Feature Necessity & Relevancy in ML Classifier Explanations

• URL: http://arxiv.org/abs/2210.15675v1
• Date: Thu, 27 Oct 2022 12:12:45 GMT
• Title: Feature Necessity & Relevancy in ML Classifier Explanations
• Authors: Xuanxiang Huang, Martin C. Cooper, Antonio Morgado, Jordi Planes, Joao Marques-Silva
• Abstract summary: Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction. It is also critical to understand whether sensitive features can occur in some explanation, or whether a non-interesting feature must occur in all explanations.
• Score: 5.232306238197686
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction. In some applications, and besides asking for an explanation, it is also critical to understand whether sensitive features can occur in some explanation, or whether a non-interesting feature must occur in all explanations. This paper starts by relating such queries respectively with the problems of relevancy and necessity in logic-based abduction. The paper then proves membership and hardness results for several families of ML classifiers. Afterwards the paper proposes concrete algorithms for two classes of classifiers. The experimental results confirm the scalability of the proposed algorithms.

Related papers

• Pyreal: A Framework for Interpretable ML Explanations [51.14710806705126]
  Pyreal is a system for generating a variety of interpretable machine learning explanations. Pyreal converts data and explanations between the feature spaces expected by the model, relevant explanation algorithms, and human users. Our studies demonstrate that Pyreal generates more useful explanations than existing systems.
  arXiv  Detail & Related papers  (2023-12-20T15:04:52Z)
• On Logic-Based Explainability with Partially Specified Inputs [1.7587442088965224]
  Missing data is often addressed when training machine learning (ML) models. But missing data also needs to be addressed when deciding predictions and when explaining those predictions. This paper studies the computation of logic-based explanations in the presence of partially specified inputs.
  arXiv  Detail & Related papers  (2023-06-27T21:09:25Z)
• A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis [128.0532113800092]
  We present a mechanistic interpretation of Transformer-based LMs on arithmetic questions. This provides insights into how information related to arithmetic is processed by LMs.
  arXiv  Detail & Related papers  (2023-05-24T11:43:47Z)
• 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)
• Complementary Explanations for Effective In-Context Learning [77.83124315634386]
  Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts. This work aims to better understand the mechanisms by which explanations are used for in-context learning.
  arXiv  Detail & Related papers  (2022-11-25T04:40:47Z)
• What Makes a Good Explanation?: A Harmonized View of Properties of Explanations [22.752085594102777]
  Interpretability provides a means for humans to verify aspects of machine learning (ML) models. Different contexts require explanations with different properties. There is a lack of standardization when it comes to properties of explanations.
  arXiv  Detail & Related papers  (2022-11-10T16:04:28Z)
• On Deciding Feature Membership in Explanations of SDD & Related Classifiers [0.685316573653194]
  The paper shows that the feature membership problem (FMP) is hard for $SigmaP$ for a broad class of classifiers. The paper proposes propositional encodings for classifiers represented with Sentential Decision Diagrams (SDDs) and for other propositional languages.
  arXiv  Detail & Related papers  (2022-02-15T16:38:53Z)
• 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)
• Probabilistic Sufficient Explanations [31.08715352013011]
  We introduce probabilistic sufficient explanations, which formulate explaining an instance of classification as choosing the "simplest" subset of features. We design a scalable algorithm for finding the desired explanations while keeping the guarantees intact. Our experiments demonstrate the effectiveness of our algorithm in finding sufficient explanations, and showcase its advantages compared to Anchors and logical explanations.
  arXiv  Detail & Related papers  (2021-05-21T04:03:10Z)
• Discrete Reasoning Templates for Natural Language Understanding [79.07883990966077]
  We present an approach that reasons about complex questions by decomposing them to simpler subquestions. We derive the final answer according to instructions in a predefined reasoning template. We show that our approach is competitive with the state-of-the-art while being interpretable and requires little supervision.
  arXiv  Detail & Related papers  (2021-04-05T18:56:56Z)
• 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.