mlsanityData to 7 Oct 2026

Evaluating and Aggregating Feature-based Model Explanations

arXiv 2005.00631 ↗First posted 1 May 2020cs.LG cs.AI cs.CYcited by 185

Not on the map. Why?

Abstract (arXiv)

A feature-based model explanation denotes how much each input feature contributes to a model's output for a given data point. As the number of proposed explanation functions grows, we lack quantitative evaluation criteria to help practitioners know when to use which explanation function. This paper proposes quantitative evaluation criteria for feature-based explanations: low sensitivity, high faithfulness, and low complexity. We devise a framework for aggregating explanation functions. We develop a procedure for learning an aggregate explanation function with lower complexity and then derive a new aggregate Shapley value explanation function that minimizes sensitivity.

Key facts. Cited by 185 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 23; 2023: 28; 2024: 56; 2025: 36; 2026: 25.

185 papers.

Sort:

By area:

  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  2. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  3. 2021To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-makingcited by 118
  4. 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimationcited by 108
  5. 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 100
  6. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  7. 2025Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Modelscited by 67
  8. 2021Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysiscited by 65
  9. 2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59
  10. 2022Framework for Evaluating Faithfulness of Local Explanationscited by 55
  11. 2022Learning to Estimate Shapley Values with Vision Transformerscited by 44
  12. 2022Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationscited by 40
38 more
  1. 2021A Survey on the Robustness of Feature Importance and Counterfactual Explanationscited by 38
  2. 2022Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysiscited by 38
  3. 2023The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantuscited by 37
  4. 2023Explain Any Concept: Segment Anything Meets Concept-Based Explanationcited by 37
  5. 2022Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measurecited by 33
  6. 2021NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weightscited by 28
  7. 2024Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarkscited by 28
  8. 2023Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Sciencecited by 25
  9. 2022Xplique: A Deep Learning Explainability Toolboxcited by 24
  10. 2022Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanationscited by 22
  11. 2022What Makes a Good Explanation?: A Harmonized View of Properties of Explanationscited by 21
  12. 2021Fooling Partial Dependence via Data Poisoningcited by 16
  13. 2021Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution Viewcited by 15
  14. 2023Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasetscited by 15
  15. 2024Global Counterfactual Directionscited by 15
  16. 2024Understanding Visual Feature Reliance through the Lens of Complexitycited by 15
  17. 2024Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metricscited by 15
  18. 2023Efficient XAI Techniques: A Taxonomic Surveycited by 14
  19. 2023Are Data-driven Explanations Robust against Out-of-distribution Data?cited by 14
  20. 2024A comprehensive study on fidelity metrics for XAIcited by 14
  21. 2024DEAL: Disentangle and Localize Concept-level Explanations for VLMscited by 14
  22. 2023Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariancecited by 13
  23. 2024Listenable Maps for Audio Classifierscited by 13
  24. 2024Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictionscited by 13
  25. 2021RELAX: Representation Learning Explainabilitycited by 12
  26. 2023Explainability of Vision Transformers: A Comprehensive Review and New Perspectivescited by 12
  27. 2024Establishing and Evaluating Trustworthy AI: Overview and Research Challengescited by 12
  28. 2024BEExAI: Benchmark to Evaluate Explainable AIcited by 11
  29. 2024Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainabilitycited by 10
  30. 2021Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualitiescited by 9
  31. 2023Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networkscited by 9
  32. 2024Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Testcited by 9
  33. 2022Negative Evidence Matters in Interpretable Histology Image Classificationcited by 8
  34. 2023Causal Analysis for Robust Interpretability of Neural Networkscited by 8
  35. 2024Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Modelscited by 8
  36. 2024A Fresh Look at Sanity Checks for Saliency Mapscited by 8
  37. 2024Benchmarking XAI Explanations with Human-Aligned Evaluationscited by 8
  38. 2022SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usabilitycited by 7

50 most cited of 185 All 185 (JSON)