Journal articles on the topic 'Counterfactual explanations'
To see the other types of publications on this topic, follow the link: Counterfactual explanations.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Counterfactual explanations.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Sia, Suzanna, Anton Belyy, Amjad Almahairi, Madian Khabsa, Luke Zettlemoyer, and Lambert Mathias. "Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 8 (June 26, 2023): 9837–45. http://dx.doi.org/10.1609/aaai.v37i8.26174.
Full textAbstract:
Evaluating an explanation's faithfulness is desired for many reasons such as trust, interpretability and diagnosing the sources of model's errors. In this work, which focuses on the NLI task, we introduce the methodology of Faithfulness-through-Counterfactuals, which first generates a counterfactual hypothesis based on the logical predicates expressed in the explanation, and then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic (i.e. if the new formula is \textit{logically satisfiable}). In contrast to existing approaches, this does not require any explanations for training a separate verification model. We first validate the efficacy of automatic counterfactual hypothesis generation, leveraging on the few-shot priming paradigm. Next, we show that our proposed metric distinguishes between human-model agreement and disagreement on new counterfactual input. In addition, we conduct a sensitivity analysis to validate that our metric is sensitive to unfaithful explanations.
2
Asher, Nicholas, Lucas De Lara, Soumya Paul, and Chris Russell. "Counterfactual Models for Fair and Adequate Explanations." Machine Learning and Knowledge Extraction 4, no. 2 (March 31, 2022): 316–49. http://dx.doi.org/10.3390/make4020014.
Full textAbstract:
Recent efforts have uncovered various methods for providing explanations that can help interpret the behavior of machine learning programs. Exact explanations with a rigorous logical foundation provide valid and complete explanations, but they have an epistemological problem: they are often too complex for humans to understand and too expensive to compute even with automated reasoning methods. Interpretability requires good explanations that humans can grasp and can compute. We take an important step toward specifying what good explanations are by analyzing the epistemically accessible and pragmatic aspects of explanations. We characterize sufficiently good, or fair and adequate, explanations in terms of counterfactuals and what we call the conundra of the explainee, the agent that requested the explanation. We provide a correspondence between logical and mathematical formulations for counterfactuals to examine the partiality of counterfactual explanations that can hide biases; we define fair and adequate explanations in such a setting. We provide formal results about the algorithmic complexity of fair and adequate explanations. We then detail two sophisticated counterfactual models, one based on causal graphs, and one based on transport theories. We show transport based models have several theoretical advantages over the competition as explanation frameworks for machine learning algorithms.
3
VanNostrand, Peter M., Huayi Zhang, Dennis M. Hofmann, and Elke A. Rundensteiner. "FACET: Robust Counterfactual Explanation Analytics." Proceedings of the ACM on Management of Data 1, no. 4 (December 8, 2023): 1–27. http://dx.doi.org/10.1145/3626729.
Full textAbstract:
Machine learning systems are deployed in domains such as hiring and healthcare, where undesired classifications can have serious ramifications for the user. Thus, there is a rising demand for explainable AI systems which provide actionable steps for lay users to obtain their desired outcome. To meet this need, we propose FACET, the first explanation analytics system which supports a user in interactively refining counterfactual explanations for decisions made by tree ensembles. As FACET's foundation, we design a novel type of counterfactual explanation called the counterfactual region. Unlike traditional counterfactuals, FACET's regions concisely describe portions of the feature space where the desired outcome is guaranteed, regardless of variations in exact feature values. This property, which we coin explanation robustness, is critical for the practical application of counterfactuals. We develop a rich set of novel explanation analytics queries which empower users to identify personalized counterfactual regions that account for their real-world circumstances. To process these queries, we develop a compact high-dimensional counterfactual region index along with index-aware query processing strategies for near real-time explanation analytics. We evaluate FACET against state-of-the-art explanation techniques on eight public benchmark datasets and demonstrate that FACET generates actionable explanations of similar quality in an order of magnitude less time while providing critical robustness guarantees. Finally, we conduct a preliminary user study which suggests that FACET's regions lead to higher user understanding than traditional counterfactuals.
4
Kenny, Eoin M., and Mark T. Keane. "On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 13 (May 18, 2021): 11575–85. http://dx.doi.org/10.1609/aaai.v35i13.17377.
Full textAbstract:
There is a growing concern that the recent progress made in AI, especially regarding the predictive competence of deep learning models, will be undermined by a failure to properly explain their operation and outputs. In response to this disquiet, counterfactual explanations have become very popular in eXplainable AI (XAI) due to their asserted computational, psychological, and legal benefits. In contrast however, semi-factuals (which appear to be equally useful) have surprisingly received no attention. Most counterfactual methods address tabular rather than image data, partly because the non-discrete nature of images makes good counterfactuals difficult to define; indeed, generating plausible counterfactual images which lie on the data manifold is also problematic. This paper advances a novel method for generating plausible counterfactuals and semi-factuals for black-box CNN classifiers doing computer vision. The present method, called PlausIble Exceptionality-based Contrastive Explanations (PIECE), modifies all “exceptional” features in a test image to be “normal” from the perspective of the counterfactual class, to generate plausible counterfactual images. Two controlled experiments compare this method to others in the literature, showing that PIECE generates highly plausible counterfactuals (and the best semi-factuals) on several benchmark measures.
5
Leofante, Francesco, and Nico Potyka. "Promoting Counterfactual Robustness through Diversity." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 19 (March 24, 2024): 21322–30. http://dx.doi.org/10.1609/aaai.v38i19.30127.
Full textAbstract:
Counterfactual explanations shed light on the decisions of black-box models by explaining how an input can be altered to obtain a favourable decision from the model (e.g., when a loan application has been rejected). However, as noted recently, counterfactual explainers may lack robustness in the sense that a minor change in the input can cause a major change in the explanation. This can cause confusion on the user side and open the door for adversarial attacks. In this paper, we study some sources of non-robustness. While there are fundamental reasons for why an explainer that returns a single counterfactual cannot be robust in all instances, we show that some interesting robustness guarantees can be given by reporting multiple rather than a single counterfactual. Unfortunately, the number of counterfactuals that need to be reported for the theoretical guarantees to hold can be prohibitively large. We therefore propose an approximation algorithm that uses a diversity criterion to select a feasible number of most relevant explanations and study its robustness empirically. Our experiments indicate that our method improves the state-of-the-art in generating robust explanations, while maintaining other desirable properties and providing competitive computational performance.
6
Delaney, Eoin, Arjun Pakrashi, Derek Greene, and Mark T. Keane. "Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ (Abstract Reprint)." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 20 (March 24, 2024): 22696. http://dx.doi.org/10.1609/aaai.v38i20.30596.
Full textAbstract:
Counterfactual explanations have emerged as a popular solution for the eXplainable AI (XAI) problem of elucidating the predictions of black-box deep-learning systems because people easily understand them, they apply across different problem domains and seem to be legally compliant. Although over 100 counterfactual methods exist in the XAI literature, each claiming to generate plausible explanations akin to those preferred by people, few of these methods have actually been tested on users (∼7%). Even fewer studies adopt a user-centered perspective; for instance, asking people for their counterfactual explanations to determine their perspective on a “good explanation”. This gap in the literature is addressed here using a novel methodology that (i) gathers human-generated counterfactual explanations for misclassified images, in two user studies and, then, (ii) compares these human-generated explanations to computationally-generated explanations for the same misclassifications. Results indicate that humans do not “minimally edit” images when generating counterfactual explanations. Instead, they make larger, “meaningful” edits that better approximate prototypes in the counterfactual class. An analysis based on “explanation goals” is proposed to account for this divergence between human and machine explanations. The implications of these proposals for future work are discussed.
7
Baron, Sam, Mark Colyvan, and David Ripley. "A Counterfactual Approach to Explanation in Mathematics." Philosophia Mathematica 28, no. 1 (December 2, 2019): 1–34. http://dx.doi.org/10.1093/philmat/nkz023.
Full textAbstract:
ABSTRACT Our goal in this paper is to extend counterfactual accounts of scientific explanation to mathematics. Our focus, in particular, is on intra-mathematical explanations: explanations of one mathematical fact in terms of another. We offer a basic counterfactual theory of intra-mathematical explanations, before modelling the explanatory structure of a test case using counterfactual machinery. We finish by considering the application of counterpossibles to mathematical explanation, and explore a second test case along these lines.
8
Schleich, Maximilian, Zixuan Geng, Yihong Zhang, and Dan Suciu. "GeCo." Proceedings of the VLDB Endowment 14, no. 9 (May 2021): 1681–93. http://dx.doi.org/10.14778/3461535.3461555.
Full textAbstract:
Machine learning is increasingly applied in high-stakes decision making that directly affect people's lives, and this leads to an increased demand for systems to explain their decisions. Explanations often take the form of counterfactuals , which consists of conveying to the end user what she/he needs to change in order to improve the outcome. Computing counterfactual explanations is challenging, because of the inherent tension between a rich semantics of the domain, and the need for real time response. In this paper we present CeCo, the first system that can compute plausible and feasible counterfactual explanations in real time. At its core, CeCo relies on a genetic algorithm, which is customized to favor searching counterfactual explanations with the smallest number of changes. To achieve real-time performance, we introduce two novel optimizations: Δ-representation of candidate counterfactuals, and partial evaluation of the classifier. We compare empirically CeCo against five other systems described in the literature, and show that it is the only system that can achieve both high quality explanations and real time answers.
9
Barzekar, Hosein, and Susan McRoy. "Achievable Minimally-Contrastive Counterfactual Explanations." Machine Learning and Knowledge Extraction 5, no. 3 (August 3, 2023): 922–36. http://dx.doi.org/10.3390/make5030048.
Full textAbstract:
Decision support systems based on machine learning models should be able to help users identify opportunities and threats. Popular model-agnostic explanation models can identify factors that support various predictions, answering questions such as “What factors affect sales?” or “Why did sales decline?”, but do not highlight what a person should or could do to get a more desirable outcome. Counterfactual explanation approaches address intervention, and some even consider feasibility, but none consider their suitability for real-time applications, such as question answering. Here, we address this gap by introducing a novel model-agnostic method that provides specific, feasible changes that would impact the outcomes of a complex Black Box AI model for a given instance and assess its real-world utility by measuring its real-time performance and ability to find achievable changes. The method uses the instance of concern to generate high-precision explanations and then applies a secondary method to find achievable minimally-contrastive counterfactual explanations (AMCC) while limiting the search to modifications that satisfy domain-specific constraints. Using a widely recognized dataset, we evaluated the classification task to ascertain the frequency and time required to identify successful counterfactuals. For a 90% accurate classifier, our algorithm identified AMCC explanations in 47% of cases (38 of 81), with an average discovery time of 80 ms. These findings verify the algorithm’s efficiency in swiftly producing AMCC explanations, suitable for real-time systems. The AMCC method enhances the transparency of Black Box AI models, aiding individuals in evaluating remedial strategies or assessing potential outcomes.
10
Chapman-Rounds, Matt, Umang Bhatt, Erik Pazos, Marc-Andre Schulz, and Konstantinos Georgatzis. "FIMAP: Feature Importance by Minimal Adversarial Perturbation." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 13 (May 18, 2021): 11433–41. http://dx.doi.org/10.1609/aaai.v35i13.17362.
Full textAbstract:
Instance-based model-agnostic feature importance explanations (LIME, SHAP, L2X) are a popular form of algorithmic transparency. These methods generally return either a weighting or subset of input features as an explanation for the classification of an instance. An alternative literature argues instead that counterfactual instances, which alter the black-box model's classification, provide a more actionable form of explanation. We present Feature Importance by Minimal Adversarial Perturbation (FIMAP), a neural network based approach that unifies feature importance and counterfactual explanations. We show that this approach combines the two paradigms, recovering the output of feature-weighting methods in continuous feature spaces, whilst indicating the direction in which the nearest counterfactuals can be found. Our method also provides an implicit confidence estimate in its own explanations, something existing methods lack. Additionally, FIMAP improves upon the speed of sampling-based methods, such as LIME, by an order of magnitude, allowing for explanation deployment in time-critical applications. We extend our approach to categorical features using a partitioned Gumbel layer and demonstrate its efficacy on standard datasets.
11
Labaien Soto, Jokin, Ekhi Zugasti Uriguen, and Xabier De Carlos Garcia. "Real-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using Autoencoders." Applied Sciences 13, no. 5 (February 24, 2023): 2912. http://dx.doi.org/10.3390/app13052912.
Full textAbstract:
Explainable Artificial Intelligence (XAI) has gained significant attention in recent years due to concerns over the lack of interpretability of Deep Learning models, which hinders their decision-making processes. To address this issue, counterfactual explanations have been proposed to elucidate the reasoning behind a model’s decisions by providing what-if statements as explanations. However, generating counterfactuals traditionally involves solving an optimization problem for each input, making it impractical for real-time feedback. Moreover, counterfactuals must meet specific criteria, including being user-driven, causing minimal changes, and staying within the data distribution. To overcome these challenges, a novel model-agnostic approach called Real-Time Guided Counterfactual Explanations (RTGCEx) is proposed. This approach utilizes autoencoders to generate real-time counterfactual explanations that adhere to these criteria by optimizing a multiobjective loss function. The performance of RTGCEx has been evaluated on two datasets: MNIST and Gearbox, a synthetic time series dataset. The results demonstrate that RTGCEx outperforms traditional methods in terms of speed and efficacy on MNIST, while also effectively identifying and rectifying anomalies in the Gearbox dataset, highlighting its versatility across different scenarios.
12
Baron, Sam. "Counterfactual Scheming." Mind 129, no. 514 (April 1, 2019): 535–62. http://dx.doi.org/10.1093/mind/fzz008.
Full textAbstract:
Abstract Mathematics appears to play a genuine explanatory role in science. But how do mathematical explanations work? Recently, a counterfactual approach to mathematical explanation has been suggested. I argue that such a view fails to differentiate the explanatory uses of mathematics within science from the non-explanatory uses. I go on to offer a solution to this problem by combining elements of the counterfactual theory of explanation with elements of a unification theory of explanation. The result is a theory according to which a counterfactual is explanatory when it is an instance of a generalized counterfactual scheme.
13
He, Ming, Boyang An, Jiwen Wang, and Hao Wen. "CETD: Counterfactual Explanations by Considering Temporal Dependencies in Sequential Recommendation." Applied Sciences 13, no. 20 (October 11, 2023): 11176. http://dx.doi.org/10.3390/app132011176.
Full textAbstract:
Providing interpretable explanations can notably enhance users’ confidence and satisfaction with regard to recommender systems. Counterfactual explanations demonstrate remarkable performance in the realm of explainable sequential recommendation. However, current counterfactual explanation models designed for sequential recommendation overlook the temporal dependencies in a user’s past behavior sequence. Furthermore, counterfactual histories should be as similar to the real history as possible to avoid conflicting with the user’s genuine behavioral preferences. This paper presents counterfactual explanations by Considering temporal dependencies (CETD), a counterfactual explanation model that utilizes a variational autoencoder (VAE) for sequential recommendation and takes into account temporal dependencies. To improve explainability, CETD employs a recurrent neural network (RNN) when generating counterfactual histories, thereby capturing both the user’s long-term preferences and short-term behavior in their real behavioral history. Meanwhile, CETD fits the distribution of reconstructed data (i.e., the counterfactual sequences generated by VAE perturbation) in a latent space, and leverages learned variance to decrease the proximity of counterfactual histories by minimizing the distance between the counterfactual sequences and the original sequence. Thorough experiments conducted on two real-world datasets demonstrate that the proposed CETD consistently surpasses current state-of-the-art methods.
14
Geng, Zixuan, Maximilian Schleich, and Dan Suciu. "Computing Rule-Based Explanations by Leveraging Counterfactuals." Proceedings of the VLDB Endowment 16, no. 3 (November 2022): 420–32. http://dx.doi.org/10.14778/3570690.3570693.
Full textAbstract:
Sophisticated machine models are increasingly used for high-stakes decisions in everyday life. There is an urgent need to develop effective explanation techniques for such automated decisions. Rule-Based Explanations have been proposed for high-stake decisions like loan applications, because they increase the users' trust in the decision. However, rule-based explanations are very inefficient to compute, and existing systems sacrifice their quality in order to achieve reasonable performance. We propose a novel approach to compute rule-based explanations, by using a different type of explanation, Counterfactual Explanations, for which several efficient systems have already been developed. We prove a Duality Theorem, showing that rule-based and counterfactual-based explanations are dual to each other, then use this observation to develop an efficient algorithm for computing rule-based explanations, which uses the counterfactual-based explanation as an oracle. We conduct extensive experiments showing that our system computes rule-based explanations of higher quality, and with the same or better performance, than two previous systems, MinSetCover and Anchor.
15
Fernandes, Alison. "Back to the Present: How Not to Use Counterfactuals to Explain Causal Asymmetry." Philosophies 7, no. 2 (April 9, 2022): 43. http://dx.doi.org/10.3390/philosophies7020043.
Full textAbstract:
A plausible thought is that we should evaluate counterfactuals in the actual world by holding the present ‘fixed’; the state of the counterfactual world at the time of the antecedent, outside the area of the antecedent, is required to match that of the actual world. When used to evaluate counterfactuals in the actual world, this requirement may produce reasonable results. However, the requirement is deeply problematic when used in the context of explaining causal asymmetry (why causes come before their effects). The requirement plays a crucial role in certain statistical mechanical explanations of the temporal asymmetry of causation. I will use a case of backwards time travel to show how the requirement enforces certain features of counterfactual structure a priori. For this reason, the requirement cannot be part of a completely general method of evaluating counterfactuals. More importantly, the way the requirement enforces features of counterfactual structure prevents counterfactual structure being derived from more fundamental physical structure—as explanations of causal asymmetry demand. Therefore, the requirement cannot be used when explaining causal asymmetry. To explain causal asymmetry, we need more temporally neutral methods for evaluating counterfactuals—those that produce the right results in cases involving backwards time travel, as well as in the actual world.
16
Aryal, Saugat. "Semi-factual Explanations in AI." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 21 (March 24, 2024): 23379–80. http://dx.doi.org/10.1609/aaai.v38i21.30390.
Full textAbstract:
Most of the recent works on post-hoc example-based eXplainable AI (XAI) methods revolves around employing counterfactual explanations to provide justification of the predictions made by AI systems. Counterfactuals show what changes to the input-features change the output decision. However, a lesser-known, special-case of the counterfacual is the semi-factual, which provide explanations about what changes to the input-features do not change the output decision. Semi-factuals are potentially as useful as counterfactuals but have received little attention in the XAI literature. My doctoral research aims to establish a comprehensive framework for the use of semi-factuals in XAI by developing novel methods for their computation, supported by user tests.
17
Fernández-Loría, Carlos, Foster Provost, and Xintian Han. "Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach." MIS Quarterly 45, no. 3 (September 1, 2022): 1635–60. http://dx.doi.org/10.25300/misq/2022/16749.
Full textAbstract:
We examine counterfactual explanations for explaining the decisions made by model-based AI systems. The counterfactual approach we consider defines an explanation as a set of the system’s data inputs that causally drives the decision (i.e., changing the inputs in the set changes the decision) and is irreducible (i.e., changing any subset of the inputs does not change the decision). We (1) demonstrate how this framework may be used to provide explanations for decisions made by general data-driven AI systems that can incorporate features with arbitrary data types and multiple predictive models, and (2) propose a heuristic procedure to find the most useful explanations depending on the context. We then contrast counterfactual explanations with methods that explain model predictions by weighting features according to their importance (e.g., Shapley additive explanations [SHAP], local interpretable model-agnostic explanations [LIME]) and present two fundamental reasons why we should carefully consider whether importance-weight explanations are well suited to explain system decisions. Specifically, we show that (1) features with a large importance weight for a model prediction may not affect the corresponding decision, and (2) importance weights are insufficient to communicate whether and how features influence decisions. We demonstrate this with several concise examples and three detailed case studies that compare the counterfactual approach with SHAP to illustrate conditions under which counterfactual explanations explain data-driven decisions better than importance weights.
18
Prado-Romero, Mario Alfonso, Bardh Prenkaj, and Giovanni Stilo. "Robust Stochastic Graph Generator for Counterfactual Explanations." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 19 (March 24, 2024): 21518–26. http://dx.doi.org/10.1609/aaai.v38i19.30149.
Full textAbstract:
Counterfactual Explanation (CE) techniques have garnered attention as a means to provide insights to the users engaging with AI systems. While extensively researched in domains such as medical imaging and autonomous vehicles, Graph Counterfactual Explanation (GCE) methods have been comparatively under-explored. GCEs generate a new graph similar to the original one, with a different outcome grounded on the underlying predictive model. Among these GCE techniques, those rooted in generative mechanisms have received relatively limited investigation despite demonstrating impressive accomplishments in other domains, such as artistic styles and natural language modelling. The preference for generative explainers stems from their capacity to generate counterfactual instances during inference, leveraging autonomously acquired perturbations of the input graph. Motivated by the rationales above, our study introduces RSGG-CE, a novel Robust Stochastic Graph Generator for Counterfactual Explanations able to produce counterfactual examples from the learned latent space considering a partially ordered generation sequence. Furthermore, we undertake quantitative and qualitative analyses to compare RSGG-CE's performance against SoA generative explainers, highlighting its increased ability to engendering plausible counterfactual candidates.
19
Vries, Katja de. "Transparent Dreams (Are Made of This): Counterfactuals as Transparency Tools in ADM." Critical Analysis of Law 8, no. 1 (April 2, 2021): 121–38. http://dx.doi.org/10.33137/cal.v8i1.36283.
Full textAbstract:
This article gives a legal-conceptual analysis of the use of counterfactuals (what-if explanations) as transparency tools for automated decision making (ADM). The first part of the analysis discusses three notions: transparency, ADM and generative artificial intelligence (AI). The second part of this article takes a closer look at the pros and cons of counterfactuals in making ADM explainable. Transparency is only useful if it is actionable, that is, if it challenges systemic bias or unjustified decisions. Existing ways of providing transparency about ADM systems are often limited in terms of being actionable. In contrast to many existing transparency tools, counterfactual explanations hold the promise of providing actionable and individually tailored transparency while not revealing too much of the model (attractive if ADM is a trade secret or if it is important that the system cannot be gamed). Another strength of counterfactuals is that they show that transparency should not be understood as the immediate visibility of some underlying truth. While promising, counterfactuals have their limitations. Firstly, there is always a multiplicity of counterfactuals (the Rashomon effect). Secondly, counterfactual explanations are not natural givens. Instead, they are constructed and the many underlying design decisions can turn out for better or worse.
20
Sokol, Kacper, and Peter Flach. "Desiderata for Interpretability: Explaining Decision Tree Predictions with Counterfactuals." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 10035–36. http://dx.doi.org/10.1609/aaai.v33i01.330110035.
Full textAbstract:
Explanations in machine learning come in many forms, but a consensus regarding their desired properties is still emerging. In our work we collect and organise these explainability desiderata and discuss how they can be used to systematically evaluate properties and quality of an explainable system using the case of class-contrastive counterfactual statements. This leads us to propose a novel method for explaining predictions of a decision tree with counterfactuals. We show that our model-specific approach exploits all the theoretical advantages of counterfactual explanations, hence improves decision tree interpretability by decoupling the quality of the interpretation from the depth and width of the tree.
21
Cong, Zicun, Lingyang Chu, Yu Yang, and Jian Pei. "Comprehensible counterfactual explanation on Kolmogorov-Smirnov test." Proceedings of the VLDB Endowment 14, no. 9 (May 2021): 1583–96. http://dx.doi.org/10.14778/3461535.3461546.
Full textAbstract:
The Kolmogorov-Smirnov (KS) test is popularly used in many applications, such as anomaly detection, astronomy, database security and AI systems. One challenge remained untouched is how we can obtain an explanation on why a test set fails the KS test. In this paper, we tackle the problem of producing counterfactual explanations for test data failing the KS test. Concept-wise, we propose the notion of most comprehensible counterfactual explanations, which accommodates both the KS test data and the user domain knowledge in producing explanations. Computation-wise, we develop an efficient algorithm MOCHE (for <u>MO</u>st <u>C</u>ompre<u>H</u>ensible <u>E</u>xplanation) that avoids enumerating and checking an exponential number of subsets of the test set failing the KS test. MOCHE not only guarantees to produce the most comprehensible counterfactual explanations, but also is orders of magnitudes faster than the baselines. Experiment-wise, we present a systematic empirical study on a series of benchmark real datasets to verify the effectiveness, efficiency and scalability of most comprehensible counterfactual explanations and MOCHE.
22
Le, Thao, Tim Miller, Ronal Singh, and Liz Sonenberg. "Explaining Model Confidence Using Counterfactuals." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 10 (June 26, 2023): 11856–64. http://dx.doi.org/10.1609/aaai.v37i10.26399.
Full textAbstract:
Displaying confidence scores in human-AI interaction has been shown to help build trust between humans and AI systems. However, most existing research uses only the confidence score as a form of communication. As confidence scores are just another model output, users may want to understand why the algorithm is confident to determine whether to accept the confidence score. In this paper, we show that counterfactual explanations of confidence scores help study participants to better understand and better trust a machine learning model's prediction. We present two methods for understanding model confidence using counterfactual explanation: (1) based on counterfactual examples; and (2) based on visualisation of the counterfactual space. Both increase understanding and trust for study participants over a baseline of no explanation, but qualitative results show that they are used quite differently, leading to recommendations of when to use each one and directions of designing better explanations.
23
Sunstein, Cass R. "Historical Explanations Always Involve Counterfactual History." Journal of the Philosophy of History 10, no. 3 (November 17, 2016): 433–40. http://dx.doi.org/10.1163/18722636-12341345.
Full textAbstract:
Historical explanations are a form of counterfactual history. To offer an explanation of what happened, historians have to identify causes, and whenever they identify causes, they immediately conjure up a counterfactual history, a parallel world. No one doubts that there is a great deal of distance between science fiction novelists and the world’s great historians, but along an important dimension, they are playing the same game.
24
Madumal, Prashan, Tim Miller, Liz Sonenberg, and Frank Vetere. "Explainable Reinforcement Learning through a Causal Lens." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 03 (April 3, 2020): 2493–500. http://dx.doi.org/10.1609/aaai.v34i03.5631.
Full textAbstract:
Prominent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal relationships. In making sense of the world, we build causal models in our mind to encode cause-effect relations of events and use these to explain why new events happen by referring to counterfactuals — things that did not happen. In this paper, we use causal models to derive causal explanations of the behaviour of model-free reinforcement learning agents. We present an approach that learns a structural causal model during reinforcement learning and encodes causal relationships between variables of interest. This model is then used to generate explanations of behaviour based on counterfactual analysis of the causal model. We computationally evaluate the model in 6 domains and measure performance and task prediction accuracy. We report on a study with 120 participants who observe agents playing a real-time strategy game (Starcraft II) and then receive explanations of the agents' behaviour. We investigate: 1) participants' understanding gained by explanations through task prediction; 2) explanation satisfaction and 3) trust. Our results show that causal model explanations perform better on these measures compared to two other baseline explanation models.
25
Lai, Chengen, Shengli Song, Shiqi Meng, Jingyang Li, Sitong Yan, and Guangneng Hu. "Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 3 (March 24, 2024): 2849–57. http://dx.doi.org/10.1609/aaai.v38i3.28065.
Full textAbstract:
Natural language explanation in visual question answer (VQA-NLE) aims to explain the decision-making process of models by generating natural language sentences to increase users' trust in the black-box systems. Existing post-hoc methods have achieved significant progress in obtaining a plausible explanation. However, such post-hoc explanations are not always aligned with human logical inference, suffering from the issues on: 1) Deductive unsatisfiability, the generated explanations do not logically lead to the answer; 2) Factual inconsistency, the model falsifies its counterfactual explanation for answers without considering the facts in images; and 3) Semantic perturbation insensitivity, the model can not recognize the semantic changes caused by small perturbations. These problems reduce the faithfulness of explanations generated by models. To address the above issues, we propose a novel self-supervised Multi-level Contrastive Learning based natural language Explanation model (MCLE) for VQA with semantic-level, image-level, and instance-level factual and counterfactual samples. MCLE extracts discriminative features and aligns the feature spaces from explanations with visual question and answer to generate more consistent explanations. We conduct extensive experiments, ablation analysis, and case study to demonstrate the effectiveness of our method on two VQA-NLE benchmarks.
26
Amitai, Yotam, Yael Septon, and Ofra Amir. "Explaining Reinforcement Learning Agents through Counterfactual Action Outcomes." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 9 (March 24, 2024): 10003–11. http://dx.doi.org/10.1609/aaai.v38i9.28863.
Full textAbstract:
Explainable reinforcement learning (XRL) methods aim to help elucidate agent policies and decision-making processes. The majority of XRL approaches focus on local explanations, seeking to shed light on the reasons an agent acts the way it does at a specific world state. While such explanations are both useful and necessary, they typically do not portray the outcomes of the agent's selected choice of action. In this work, we propose ``COViz'', a new local explanation method that visually compares the outcome of an agent's chosen action to a counterfactual one. In contrast to most local explanations that provide state-limited observations of the agent's motivation, our method depicts alternative trajectories the agent could have taken from the given state and their outcomes. We evaluated the usefulness of COViz in supporting people's understanding of agents' preferences and compare it with reward decomposition, a local explanation method that describes an agent's expected utility for different actions by decomposing it into meaningful reward types. Furthermore, we examine the complementary benefits of integrating both methods. Our results show that such integration significantly improved participants' performance.
27
McEleney, Alice, and Ruth M. J. Byrne. "Spontaneous counterfactual thoughts and causal explanations." Thinking & Reasoning 12, no. 2 (May 2006): 235–55. http://dx.doi.org/10.1080/13546780500317897.
Full text
28
Lucic, Ana, Harrie Oosterhuis, Hinda Haned, and Maarten de Rijke. "FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 5 (June 28, 2022): 5313–22. http://dx.doi.org/10.1609/aaai.v36i5.20468.
Full textAbstract:
Model interpretability has become an important problem in machine learning (ML) due to the increased effect algorithmic decisions have on humans. Counterfactual explanations can help users understand not only why ML models make certain decisions, but also how these decisions can be changed. We frame the problem of finding counterfactual explanations as an optimization task and extend previous work that could only be applied to differentiable models. In order to accommodate non-differentiable models such as tree ensembles, we use probabilistic model approximations in the optimization framework. We introduce an approximation technique that is effective for finding counterfactual explanations for predictions of the original model and show that our counterfactual examples are significantly closer to the original instances than those produced by other methods specifically designed for tree ensembles.
29
Lee, Min Hun, and Chong Jun Chew. "Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making." Proceedings of the ACM on Human-Computer Interaction 7, CSCW2 (September 28, 2023): 1–22. http://dx.doi.org/10.1145/3610218.
Full textAbstract:
Artificial intelligence (AI) is increasingly being considered to assist human decision-making in high-stake domains (e.g. health). However, researchers have discussed an issue that humans can over-rely on wrong suggestions of the AI model instead of achieving human AI complementary performance. In this work, we utilized salient feature explanations along with what-if, counterfactual explanations to make humans review AI suggestions more analytically to reduce overreliance on AI and explored the effect of these explanations on trust and reliance on AI during clinical decision-making. We conducted an experiment with seven therapists and ten laypersons on the task of assessing post-stroke survivors' quality of motion, and analyzed their performance, agreement level on the task, and reliance on AI without and with two types of AI explanations. Our results showed that the AI model with both salient features and counterfactual explanations assisted therapists and laypersons to improve their performance and agreement level on the task when 'right' AI outputs are presented. While both therapists and laypersons over-relied on 'wrong' AI outputs, counterfactual explanations assisted both therapists and laypersons to reduce their over-reliance on 'wrong' AI outputs by 21% compared to salient feature explanations. Specifically, laypersons had higher performance degrades by 18.0 f1-score with salient feature explanations and 14.0 f1-score with counterfactual explanations than therapists with performance degrades of 8.6 and 2.8 f1-scores respectively. Our work discusses the potential of counterfactual explanations to better estimate the accuracy of an AI model and reduce over-reliance on 'wrong' AI outputs and implications for improving human-AI collaborative decision-making.
30
Carreira-Perpiñán, Miguel Á., and Suryabhan Singh Hada. "Counterfactual Explanations for Oblique Decision Trees:Exact, Efficient Algorithms." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 8 (May 18, 2021): 6903–11. http://dx.doi.org/10.1609/aaai.v35i8.16851.
Full textAbstract:
We consider counterfactual explanations, the problem of minimally adjusting features in a source input instance so that it is classified as a target class under a given classifier. This has become a topic of recent interest as a way to query a trained model and suggest possible actions to overturn its decision. Mathematically, the problem is formally equivalent to that of finding adversarial examples, which also has attracted significant attention recently. Most work on either counterfactual explanations or adversarial examples has focused on differentiable classifiers, such as neural nets. We focus on classification trees, both axis-aligned and oblique (having hyperplane splits). Although here the counterfactual optimization problem is nonconvex and nondifferentiable, we show that an exact solution can be computed very efficiently, even with high-dimensional feature vectors and with both continuous and categorical features, and demonstrate it in different datasets and settings. The results are particularly relevant for finance, medicine or legal applications, where interpretability and counterfactual explanations are particularly important.
31
Altmeyer, Patrick, Mojtaba Farmanbar, Arie Van Deursen, and Cynthia C. S. Liem. "Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 10 (March 24, 2024): 10829–37. http://dx.doi.org/10.1609/aaai.v38i10.28956.
Full textAbstract:
Counterfactual explanations offer an intuitive and straightforward way to explain black-box models and offer algorithmic recourse to individuals. To address the need for plausible explanations, existing work has primarily relied on surrogate models to learn how the input data is distributed. This effectively reallocates the task of learning realistic explanations for the data from the model itself to the surrogate. Consequently, the generated explanations may seem plausible to humans but need not necessarily describe the behaviour of the black-box model faithfully. We formalise this notion of faithfulness through the introduction of a tailored evaluation metric and propose a novel algorithmic framework for generating Energy-Constrained Conformal Counterfactuals that are only as plausible as the model permits. Through extensive empirical studies, we demonstrate that ECCCo reconciles the need for faithfulness and plausibility. In particular, we show that for models with gradient access, it is possible to achieve state-of-the-art performance without the need for surrogate models. To do so, our framework relies solely on properties defining the black-box model itself by leveraging recent advances in energy-based modelling and conformal prediction. To our knowledge, this is the first venture in this direction for generating faithful counterfactual explanations. Thus, we anticipate that ECCCo can serve as a baseline for future research. We believe that our work opens avenues for researchers and practitioners seeking tools to better distinguish trustworthy from unreliable models.
32
Gulshad, Sadaf, and Arnold Smeulders. "Counterfactual attribute-based visual explanations for classification." International Journal of Multimedia Information Retrieval 10, no. 2 (April 18, 2021): 127–40. http://dx.doi.org/10.1007/s13735-021-00208-3.
Full textAbstract:
AbstractIn this paper, our aim is to provide human understandable intuitive factual and counterfactual explanations for the decisions of neural networks. Humans tend to reinforce their decisions by providing attributes and counterattributes. Hence, in this work, we utilize attributes as well as examples to provide explanations. In order to provide counterexplanations we make use of directed perturbations to arrive at the counterclass attribute values in doing so, we explain what is present and what is absent in the original image. We evaluate our method when images are misclassified into closer counterclasses as well as when misclassified into completely different counterclasses. We conducted experiments on both finegrained as well as coarsegrained datasets. We verified our attribute-based explanations method both quantitatively and qualitatively and showed that attributes provide discriminating and human understandable explanations for both standard as well as robust networks.
33
Yacoby, Yaniv, Ben Green, Christopher L. Griffin Jr., and Finale Doshi-Velez. "“If it didn’t happen, why would I change my decision?”: How Judges Respond to Counterfactual Explanations for the Public Safety Assessment." Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 10, no. 1 (October 14, 2022): 219–30. http://dx.doi.org/10.1609/hcomp.v10i1.22001.
Full textAbstract:
Many researchers and policymakers have expressed excitement about algorithmic explanations enabling more fair and responsible decision-making. However, recent experimental studies have found that explanations do not always improve human use of algorithmic advice. In this study, we shed light on how people interpret and respond to counterfactual explanations (CFEs)---explanations that show how a model's output would change with marginal changes to its input(s)---in the context of pretrial risk assessment instruments (PRAIs). We ran think-aloud trials with eight sitting U.S. state court judges, providing them with recommendations from a PRAI that includes CFEs. We found that the CFEs did not alter the judges' decisions. At first, judges misinterpreted the counterfactuals as real---rather than hypothetical---changes to defendants. Once judges understood what the counterfactuals meant, they ignored them, stating their role is only to make decisions regarding the actual defendant in question. The judges also expressed a mix of reasons for ignoring or following the advice of the PRAI without CFEs. These results add to the literature detailing the unexpected ways in which people respond to algorithms and explanations. They also highlight new challenges associated with improving human-algorithm collaborations through explanations.
34
Virmajoki, Veli. "Frameworks in Historiography: Explanation, Scenarios, and Futures." Journal of the Philosophy of History 17, no. 2 (July 3, 2023): 288–309. http://dx.doi.org/10.1163/18722636-12341501.
Full textAbstract:
Abstract In this paper, I analyze how frameworks shape historiographical explanations. I argue that, in order to identify a sequence of events as relevant to a historical outcome, assumptions about the workings of the relevant domain have to be made. By extending Lakatosian considerations, I argue that these assumptions are provided by a framework that contains a set of factors and intertwined principles that (supposedly) govern how a historical phenomenon works. I connect frameworks with a counterfactual account of historical explanation. Frameworks enable us to explain the past by providing a backbone of explanatory patterns of counterfactual dependency. I conclude by noting that both counterfactual scenarios and scenarios of the future require frameworks and, therefore, historiographical explanation generates a set of possible futures. Analyzing these possible futures enables us to reveal the theoretical commitments of historiography.
35
Ley, Dan, Umang Bhatt, and Adrian Weller. "Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7390–98. http://dx.doi.org/10.1609/aaai.v36i7.20702.
Full textAbstract:
To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating a single Counterfactual Latent Uncertainty Explanation (CLUE) for a given data point where the model is uncertain. We broaden the exploration to examine δ-CLUE, the set of potential CLUEs within a δ ball of the original input in latent space. We study the diversity of such sets and find that many CLUEs are redundant; as such, we propose DIVerse CLUE (∇-CLUE), a set of CLUEs which each propose a distinct explanation as to how one can decrease the uncertainty associated with an input. We then further propose GLobal AMortised CLUE (GLAM-CLUE), a distinct, novel method which learns amortised mappings that apply to specific groups of uncertain inputs, taking them and efficiently transforming them in a single function call into inputs for which a model will be certain. Our experiments show that δ-CLUE, ∇-CLUE, and GLAM-CLUE all address shortcomings of CLUE and provide beneficial explanations of uncertainty estimates to practitioners.
36
Wellawatte, Geemi P., Aditi Seshadri, and Andrew D. White. "Model agnostic generation of counterfactual explanations for molecules." Chemical Science 13, no. 13 (2022): 3697–705. http://dx.doi.org/10.1039/d1sc05259d.
Full text
37
Piccione, A., J. W. Berkery, S. A. Sabbagh, and Y. Andreopoulos. "Predicting resistive wall mode stability in NSTX through balanced random forests and counterfactual explanations." Nuclear Fusion 62, no. 3 (January 18, 2022): 036002. http://dx.doi.org/10.1088/1741-4326/ac44af.
Full textAbstract:
Abstract Recent progress in the disruption event characterization and forecasting framework has shown that machine learning guided by physics theory can be easily implemented as a supporting tool for fast computations of ideal stability properties of spherical tokamak plasmas. In order to extend that idea, a customized random forest (RF) classifier that takes into account imbalances in the training data is hereby employed to predict resistive wall mode (RWM) stability for a set of high beta discharges from the NSTX spherical tokamak. More specifically, with this approach each tree in the forest is trained on samples that are balanced via a user-defined over/under-sampler. The proposed approach outperforms classical cost-sensitive methods for the problem at hand, in particular when used in conjunction with a random under-sampler, while also resulting in a threefold reduction in the training time. In order to further understand the model’s decisions, a diverse set of counterfactual explanations based on determinantal point processes (DPP) is generated and evaluated. Via the use of DPP, the underlying RF model infers that the presence of hypothetical magnetohydrodynamic activity would have prevented the RWM from concurrently going unstable, which is a counterfactual that is indeed expected by prior physics knowledge. Given that this result emerges from the data-driven RF classifier and the use of counterfactuals without hand-crafted embedding of prior physics intuition, it motivates the usage of counterfactuals to simulate real-time control by generating the β N levels that would have kept the RWM stable for a set of unstable discharges.
38
Jiang, Junqi, Francesco Leofante, Antonio Rago, and Francesca Toni. "Formalising the Robustness of Counterfactual Explanations for Neural Networks." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 12 (June 26, 2023): 14901–9. http://dx.doi.org/10.1609/aaai.v37i12.26740.
Full textAbstract:
The use of counterfactual explanations (CFXs) is an increasingly popular explanation strategy for machine learning models. However, recent studies have shown that these explanations may not be robust to changes in the underlying model (e.g., following retraining), which raises questions about their reliability in real-world applications. Existing attempts towards solving this problem are heuristic, and the robustness to model changes of the resulting CFXs is evaluated with only a small number of retrained models, failing to provide exhaustive guarantees. To remedy this, we propose ∆-robustness, the first notion to formally and deterministically assess the robustness (to model changes) of CFXs for neural networks. We introduce an abstraction framework based on interval neural networks to verify the ∆-robustness of CFXs against a possibly infinite set of changes to the model parameters, i.e., weights and biases. We then demonstrate the utility of this approach in two distinct ways. First, we analyse the ∆-robustness of a number of CFX generation methods from the literature and show that they unanimously host significant deficiencies in this regard. Second, we demonstrate how embedding ∆-robustness within existing methods can provide CFXs which are provably robust.
39
de Oliveira, Raphael Mazzine Barbosa, and David Martens. "A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data." Applied Sciences 11, no. 16 (August 7, 2021): 7274. http://dx.doi.org/10.3390/app11167274.
Full textAbstract:
Counterfactual explanations are viewed as an effective way to explain machine learning predictions. This interest is reflected by a relatively young literature with already dozens of algorithms aiming to generate such explanations. These algorithms are focused on finding how features can be modified to change the output classification. However, this rather general objective can be achieved in different ways, which brings about the need for a methodology to test and benchmark these algorithms. The contributions of this work are manifold: First, a large benchmarking study of 10 algorithmic approaches on 22 tabular datasets is performed, using nine relevant evaluation metrics; second, the introduction of a novel, first of its kind, framework to test counterfactual generation algorithms; third, a set of objective metrics to evaluate and compare counterfactual results; and, finally, insight from the benchmarking results that indicate which approaches obtain the best performance on what type of dataset. This benchmarking study and framework can help practitioners in determining which technique and building blocks most suit their context, and can help researchers in the design and evaluation of current and future counterfactual generation algorithms. Our findings show that, overall, there’s no single best algorithm to generate counterfactual explanations as the performance highly depends on properties related to the dataset, model, score, and factual point specificities.
40
Akula, Arjun, Shuai Wang, and Song-Chun Zhu. "CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 03 (April 3, 2020): 2594–601. http://dx.doi.org/10.1609/aaai.v34i03.5643.
Full textAbstract:
We present CoCoX (short for Conceptual and Counterfactual Explanations), a model for explaining decisions made by a deep convolutional neural network (CNN). In Cognitive Psychology, the factors (or semantic-level features) that humans zoom in on when they imagine an alternative to a model prediction are often referred to as fault-lines. Motivated by this, our CoCoX model explains decisions made by a CNN using fault-lines. Specifically, given an input image I for which a CNN classification model M predicts class cpred, our fault-line based explanation identifies the minimal semantic-level features (e.g., stripes on zebra, pointed ears of dog), referred to as explainable concepts, that need to be added to or deleted from I in order to alter the classification category of I by M to another specified class calt. We argue that, due to the conceptual and counterfactual nature of fault-lines, our CoCoX explanations are practical and more natural for both expert and non-expert users to understand the internal workings of complex deep learning models. Extensive quantitative and qualitative experiments verify our hypotheses, showing that CoCoX significantly outperforms the state-of-the-art explainable AI models. Our implementation is available at https://github.com/arjunakula/CoCoX
41
Reutlinger, Alexander. "Does the counterfactual theory of explanation apply to non-causal explanations in metaphysics?" European Journal for Philosophy of Science 7, no. 2 (August 19, 2016): 239–56. http://dx.doi.org/10.1007/s13194-016-0155-z.
Full text
42
Carreira-Perpinan, Miguel Á., and Suryabhan Singh Hada. "Very Fast, Approximate Counterfactual Explanations for Decision Forests." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 6 (June 26, 2023): 6935–43. http://dx.doi.org/10.1609/aaai.v37i6.25848.
Full textAbstract:
We consider finding a counterfactual explanation for a classification or regression forest, such as a random forest. This requires solving an optimization problem to find the closest input instance to a given instance for which the forest outputs a desired value. Finding an exact solution has a cost that is exponential on the number of leaves in the forest. We propose a simple but very effective approach: we constrain the optimization to input space regions populated by actual data points. The problem reduces to a form of nearest-neighbor search using a certain distance on a certain dataset. This has two advantages: first, the solution can be found very quickly, scaling to large forests and high-dimensional data, and enabling interactive use. Second, the solution found is more likely to be realistic in that it is guided towards high-density areas of input space.
43
Chalyi, Serhii, Volodymyr Leshchynskyi, and Irina Leshchynska. "COUNTERFACTUAL TEMPORAL MODEL OF CAUSAL RELATIONSHIPS FOR CONSTRUCTING EXPLANATIONS IN INTELLIGENT SYSTEMS." Bulletin of National Technical University "KhPI". Series: System Analysis, Control and Information Technologies, no. 2 (6) (December 28, 2021): 41–46. http://dx.doi.org/10.20998/2079-0023.2021.02.07.
Full textAbstract:
The subject of the research is the processes of constructing explanations based on causal relationships between states or actions of an intellectualsystem. An explanation is knowledge about the sequence of causes and effects that determine the process and result of an intelligent informationsystem. The aim of the work is to develop a counterfactual temporal model of cause-and-effect relationships as part of an explanation of the process offunctioning of an intelligent system in order to ensure the identification of causal dependencies based on the analysis of the logs of the behavior ofsuch a system. To achieve the stated goals, the following tasks are solved: determination of the temporal properties of the counterfactual description ofcause-and-effect relationships between actions or states of an intelligent information system; development of a temporal model of causal connections,taking into account both the facts of occurrence of events in the intellectual system, and the possibility of occurrence of events that do not affect theformation of the current decision. Conclusions. The structuring of the temporal properties of causal links for pairs of events that occur sequentially intime or have intermediate events is performed. Such relationships are represented by alternative causal relationships using the temporal operators"Next" and "Future", which allows realizing a counterfactual approach to the representation of causality. A counterfactual temporal model of causalrelationships is proposed, which determines deterministic causal relationships for pairs of consecutive events and pairs of events between which thereare other events, which determines the transitivity property of such dependencies and, accordingly, creates conditions for describing the sequence ofcauses and effects as part of the explanation in intelligent system with a given degree of detail The model provides the ability to determine cause-andeffect relationships, between which there are intermediate events that do not affect the final result of the intelligent information system.
44
Admassu, Tsehay. "Evaluation of Local Interpretable Model-Agnostic Explanation and Shapley Additive Explanation for Chronic Heart Disease Detection." Proceedings of Engineering and Technology Innovation 23 (January 1, 2023): 48–59. http://dx.doi.org/10.46604/peti.2023.10101.
Full textAbstract:
This study aims to investigate the effectiveness of local interpretable model-agnostic explanation (LIME) and Shapley additive explanation (SHAP) approaches for chronic heart disease detection. The efficiency of LIME and SHAP are evaluated by analyzing the diagnostic results of the XGBoost model and the stability and quality of counterfactual explanations. Firstly, 1025 heart disease samples are collected from the University of California Irvine. Then, the performance of LIME and SHAP is compared by using the XGBoost model with various measures, such as consistency and proximity. Finally, Python 3.7 programming language with Jupyter Notebook integrated development environment is used for simulation. The simulation result shows that the XGBoost model achieves 99.79% accuracy, indicating that the counterfactual explanation of the XGBoost model describes the smallest changes in the feature values for changing the diagnosis outcome to the predefined output.
45
Zahedi, Zahra, Sailik Sengupta, and Subbarao Kambhampati. "‘Why Didn’t You Allocate This Task to Them?’ Negotiation-Aware Task Allocation and Contrastive Explanation Generation." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 9 (March 24, 2024): 10243–51. http://dx.doi.org/10.1609/aaai.v38i9.28890.
Full textAbstract:
In this work, we design an Artificially Intelligent Task Allocator (AITA) that proposes a task allocation for a team of humans. A key property of this allocation is that when an agent with imperfect knowledge (about their teammate's costs and/or the team's performance metric) contests the allocation with a counterfactual, a contrastive explanation can always be provided to showcase why the proposed allocation is better than the proposed counterfactual. For this, we consider a negotiation process that produces a negotiation-aware task allocation and, when contested, leverages a negotiation tree to provide a contrastive explanation. With human subject studies, we show that the proposed allocation indeed appears fair to a majority of participants and, when not, the explanations generated are judged as convincing and easy to comprehend.
46
Nolan, Daniel. "The Possibilities of History." Journal of the Philosophy of History 10, no. 3 (November 17, 2016): 441–56. http://dx.doi.org/10.1163/18722636-12341346.
Full textAbstract:
Several kinds of historical alternatives are distinguished. Different kinds of historical alternatives are valuable to the practice of history for different reasons. Important uses for historical alternatives include representing different sides of historical disputes; distributing chances of different outcomes over alternatives; and offering explanations of why various alternatives did not in fact happen. Consideration of counterfactuals about what would have happened had things been different in particular ways plays particularly useful roles in reasoning about historical analogues of current conditions; reasoning about causal claims; and in evaluating historical explanations. When evaluating the role of alternative histories in historical thinking, we should keep in mind the uses of historical alternatives that go well beyond the long-term and specific scenarios that are the focus of so-called “counterfactual history”.
47
de Brito Duarte, Regina, Filipa Correia, Patrícia Arriaga, and Ana Paiva. "AI Trust: Can Explainable AI Enhance Warranted Trust?" Human Behavior and Emerging Technologies 2023 (October 31, 2023): 1–12. http://dx.doi.org/10.1155/2023/4637678.
Full textAbstract:
Explainable artificial intelligence (XAI), known to produce explanations so that predictions from AI models can be understood, is commonly used to mitigate possible AI mistrust. The underlying premise is that the explanations of the XAI models enhance AI trust. However, such an increase may depend on many factors. This article examined how trust in an AI recommendation system is affected by the presence of explanations, the performance of the system, and the level of risk. Our experimental study, conducted with 215 participants, has shown that the presence of explanations increases AI trust, but only in certain conditions. AI trust was higher when explanations with feature importance were provided than with counterfactual explanations. Moreover, when the system performance is not guaranteed, the use of explanations seems to lead to an overreliance on the system. Lastly, system performance had a stronger impact on trust, compared to the effects of other factors (explanation and risk).
48
Freiesleben, Timo. "The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples." Minds and Machines 32, no. 1 (October 30, 2021): 77–109. http://dx.doi.org/10.1007/s11023-021-09580-9.
Full textAbstract:
AbstractThe same method that creates adversarial examples (AEs) to fool image-classifiers can be used to generate counterfactual explanations (CEs) that explain algorithmic decisions. This observation has led researchers to consider CEs as AEs by another name. We argue that the relationship to the true label and the tolerance with respect to proximity are two properties that formally distinguish CEs and AEs. Based on these arguments, we introduce CEs, AEs, and related concepts mathematically in a common framework. Furthermore, we show connections between current methods for generating CEs and AEs, and estimate that the fields will merge more and more as the number of common use-cases grows.
49
Guidotti, Riccardo, Anna Monreale, Fosca Giannotti, Dino Pedreschi, Salvatore Ruggieri, and Franco Turini. "Factual and Counterfactual Explanations for Black Box Decision Making." IEEE Intelligent Systems 34, no. 6 (November 1, 2019): 14–23. http://dx.doi.org/10.1109/mis.2019.2957223.
Full text
50
Wang, Xiangmeng, Qian Li, Dianer Yu, Qing Li, and Guandong Xu. "Counterfactual Explanation for Fairness in Recommendation." ACM Transactions on Information Systems, January 29, 2024. http://dx.doi.org/10.1145/3643670.
Full textAbstract:
Fairness-aware recommendation alleviates discrimination issues to build trustworthy recommendation systems. Explaining the causes of unfair recommendations is critical, as it promotes fairness diagnostics, and thus secures users’ trust in recommendation models. Existing fairness explanation methods suffer high computation burdens due to the large-scale search space and the greedy nature of the explanation search process. Besides, they perform feature-level optimizations with continuous values, which are not applicable to discrete attributes such as gender and age. In this work, we adopt counterfactual explanations from causal inference and propose to generate attribute-level counterfactual explanations, adapting to discrete attributes in recommendation models. We use real-world attributes from Heterogeneous Information Networks (HINs) to empower counterfactual reasoning on discrete attributes. We propose a Counterfactual Explanation for Fairness (CFairER) that generates attribute-level counterfactual explanations from HINs for item exposure fairness. Our CFairER conducts off-policy reinforcement learning to seek high-quality counterfactual explanations, with attentive action pruning reducing the search space of candidate counterfactuals. The counterfactual explanations help to provide rational and proximate explanations for model fairness, while the attentive action pruning narrows the search space of attributes. Extensive experiments demonstrate our proposed model can generate faithful explanations while maintaining favorable recommendation performance.