Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation

• URL: http://arxiv.org/abs/2408.03915v1
• Date: Wed, 7 Aug 2024 17:20:52 GMT
• Title: Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation
• Authors: Guy Amir, Shahaf Bassan, Guy Katz,
• Abstract summary: The ability to interpret Machine Learning (ML) models is becoming increasingly essential. Recent work has demonstrated that it is possible to formally assess interpretability by studying the computational complexity of explaining the decisions of various models.
• Score: 0.9558392439655016
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The ability to interpret Machine Learning (ML) models is becoming increasingly essential. However, despite significant progress in the field, there remains a lack of rigorous characterization regarding the innate interpretability of different models. In an attempt to bridge this gap, recent work has demonstrated that it is possible to formally assess interpretability by studying the computational complexity of explaining the decisions of various models. In this setting, if explanations for a particular model can be obtained efficiently, the model is considered interpretable (since it can be explained ``easily''). However, if generating explanations over an ML model is computationally intractable, it is considered uninterpretable. Prior research identified two key factors that influence the complexity of interpreting an ML model: (i) the type of the model (e.g., neural networks, decision trees, etc.); and (ii) the form of explanation (e.g., contrastive explanations, Shapley values, etc.). In this work, we claim that a third, important factor must also be considered for this analysis -- the underlying distribution over which the explanation is obtained. Considering the underlying distribution is key in avoiding explanations that are socially misaligned, i.e., convey information that is biased and unhelpful to users. We demonstrate the significant influence of the underlying distribution on the resulting overall interpretation complexity, in two settings: (i) prediction models paired with an external out-of-distribution (OOD) detector; and (ii) prediction models designed to inherently generate socially aligned explanations. Our findings prove that the expressiveness of the distribution can significantly influence the overall complexity of interpretation, and identify essential prerequisites that a model must possess to generate socially aligned explanations.

Related papers

• Counterfactual explainability of black-box prediction models [4.14360329494344]
  We propose a new notion called counterfactual explainability for black-box prediction models. Counterfactual explainability has three key advantages.
  arXiv  Detail & Related papers  (2024-11-03T16:29:09Z)
• Identifiable Latent Neural Causal Models [82.14087963690561]
  Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. We determine the types of distribution shifts that do contribute to the identifiability of causal representations. We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
  arXiv  Detail & Related papers  (2024-03-23T04:13:55Z)
• Explaining Causal Models with Argumentation: the Case of Bi-variate Reinforcement [15.947501347927687]
  We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models. The conceptualisation is based on reinterpreting desirable properties of semantics of AFs as explanation moulds. We perform a theoretical evaluation of these argumentative explanations, examining whether they satisfy a range of desirable explanatory and argumentative properties.
  arXiv  Detail & Related papers  (2022-05-23T19:39:51Z)
• ExSum: From Local Explanations to Model Understanding [6.23934576145261]
  Interpretability methods are developed to understand the working mechanisms of black-box models. Fulfilling this goal requires both that the explanations generated by these methods are correct and that people can easily and reliably understand them. We introduce explanation summary (ExSum), a mathematical framework for quantifying model understanding.
  arXiv  Detail & Related papers  (2022-04-30T02:07:20Z)
• Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models [77.34726150561087]
  We define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. This paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications.
  arXiv  Detail & Related papers  (2022-03-30T05:59:50Z)
• Deconfounding to Explanation Evaluation in Graph Neural Networks [136.73451468551656]
  We argue that a distribution shift exists between the full graph and the subgraph, causing the out-of-distribution problem. We propose Deconfounded Subgraph Evaluation (DSE) which assesses the causal effect of an explanatory subgraph on the model prediction.
  arXiv  Detail & Related papers  (2022-01-21T18:05:00Z)
• Do not explain without context: addressing the blind spot of model explanations [2.280298858971133]
  This paper highlights a blind spot which is often overlooked when monitoring and auditing machine learning models. We discuss that many model explanations depend directly or indirectly on the choice of the referenced data distribution. We showcase examples where small changes in the distribution lead to drastic changes in the explanations, such as a change in trend or, alarmingly, a conclusion.
  arXiv  Detail & Related papers  (2021-05-28T12:48:40Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)
• Understanding Neural Abstractive Summarization Models via Uncertainty [54.37665950633147]
  seq2seq abstractive summarization models generate text in a free-form manner. We study the entropy, or uncertainty, of the model's token-level predictions. We show that uncertainty is a useful perspective for analyzing summarization and text generation models more broadly.
  arXiv  Detail & Related papers  (2020-10-15T16:57:27Z)
• The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets [61.66584140190247]
  We show that feature-based explanations pose problems even for explaining trivial models. We show that two popular classes of explainers, Shapley explainers and minimal sufficient subsets explainers, target fundamentally different types of ground-truth explanations.
  arXiv  Detail & Related papers  (2020-09-23T09:45:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.