Generating Likely Counterfactuals Using Sum-Product Networks

• URL: http://arxiv.org/abs/2401.14086v3
• Date: Sun, 22 Sep 2024 21:39:22 GMT
• Title: Generating Likely Counterfactuals Using Sum-Product Networks
• Authors: Jiri Nemecek, Tomas Pevny, Jakub Marecek,
• Abstract summary: We show that the search for the most likely explanations satisfying many common desiderata for counterfactual explanations can be modeled using mixed-integer optimization (MIO) In the process, we propose an MIO formulation of a Sum-Product Network (SPN) and use the SPN to estimate the likelihood of a counterfactual.
• Score: 2.457872341625575
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Explainability of decisions made by AI systems is driven by both recent regulation and user demand. These decisions are often explainable only \emph{post hoc}, after the fact. In counterfactual explanations, one may ask what constitutes the best counterfactual explanation. Clearly, multiple criteria must be taken into account, although "distance from the sample" is a key criterion. Recent methods that consider the plausibility of a counterfactual seem to sacrifice this original objective. Here, we present a system that provides high-likelihood explanations that are, at the same time, close and sparse. We show that the search for the most likely explanations satisfying many common desiderata for counterfactual explanations can be modeled using mixed-integer optimization (MIO). In the process, we propose an MIO formulation of a Sum-Product Network (SPN) and use the SPN to estimate the likelihood of a counterfactual, which can be of independent interest.

Related papers

• Sparse Prototype Network for Explainable Pedestrian Behavior Prediction [60.80524827122901]
  We present Sparse Prototype Network (SPN), an explainable method designed to simultaneously predict a pedestrian's future action, trajectory, and pose. Regularized by mono-semanticity and clustering constraints, the prototypes learn consistent and human-understandable features.
  arXiv  Detail & Related papers  (2024-10-16T03:33:40Z)
• CountARFactuals -- Generating plausible model-agnostic counterfactual explanations with adversarial random forests [9.598670034160763]
  ARFs can serve as a plausibility measure or directly generate counterfactual explanations. It is easy to train and computationally highly efficient, handles continuous and categorical data naturally, and allows integrating additional desiderata such as sparsity in a straightforward manner.
  arXiv  Detail & Related papers  (2024-04-04T15:10:13Z)
• Explaining Explanations in Probabilistic Logic Programming [0.0]
  In most approaches, the system is considered a black box, making it difficult to generate appropriate explanations. We consider a setting where models are transparent: probabilistic logic programming (PLP), a paradigm that combines logic programming for knowledge representation and probability to model uncertainty. We present in this paper an approach to explaining explanations which is based on defining a new query-driven inference mechanism for PLP where proofs are labeled with "choice expressions", a compact and easy to manipulate representation for sets of choices.
  arXiv  Detail & Related papers  (2024-01-30T14:27:37Z)
• Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting [80.9896041501715]
  Explanations that have not been "tuned" for a task, such as off-the-shelf explanations written by nonexperts, may lead to mediocre performance. This paper tackles the problem of how to optimize explanation-infused prompts in a blackbox fashion.
  arXiv  Detail & Related papers  (2023-02-09T18:02:34Z)
• MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization [55.60306377044225]
  State-of-the-art summarization systems can generate highly fluent summaries. These summaries, however, may contain factual inconsistencies and/or information not present in the source. We introduce an alternative scheme based on standard information-theoretic measures in which the information present in the source and summary is directly compared.
  arXiv  Detail & Related papers  (2023-01-28T23:08:25Z)
• On Computing Probabilistic Abductive Explanations [30.325691263226968]
  The most widely studied explainable AI (XAI) approaches are unsound. PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. This paper investigates practical approaches for computing relevant sets for a number of widely used classifiers.
  arXiv  Detail & Related papers  (2022-12-12T15:47:10Z)
• Outlier Explanation via Sum-Product Networks [10.1303427221932]
  Outlier explanation is the task of identifying a set of features that distinguish a sample from normal data. Existing methods are based on beam search in the space of feature subsets. We propose a novel outlier explanation algorithm based on Sum-Product Networks (SPNs)
  arXiv  Detail & Related papers  (2022-07-18T07:47:36Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)
• Rationales for Sequential Predictions [117.93025782838123]
  Sequence models are a critical component of modern NLP systems, but their predictions are difficult to explain. We consider model explanations though rationales, subsets of context that can explain individual model predictions. We propose an efficient greedy algorithm to approximate this objective.
  arXiv  Detail & Related papers  (2021-09-14T01:25:15Z)
• Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals [72.00815192668193]
  Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time. We study several under-explored dimensions of FI-based explanations, providing conceptual and empirical improvements for this form of explanation.
  arXiv  Detail & Related papers  (2021-06-01T20:36:48Z)
• Counterfactual Explanations for Neural Recommenders [10.880181451789266]
  We propose ACCENT, the first general framework for finding counterfactual explanations for neural recommenders. We use ACCENT to generate counterfactual explanations for two popular neural models.
  arXiv  Detail & Related papers  (2021-05-11T13:16:18Z)

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.