mlsanityData to 13 Oct 2026

Debiasing Concept-based Explanations with Causal Analysis

arXiv 2007.11500 ↗First posted 22 Jul 2020cs.LG stat.MLcited by 32

Not on the map. Why?

Abstract (arXiv)

Concept-based explanation approach is a popular model interpertability tool because it expresses the reasons for a model's predictions in terms of concepts that are meaningful for the domain experts. In this work, we study the problem of the concepts being correlated with confounding information in the features. We propose a new causal prior graph for modeling the impacts of unobserved variables and a method to remove the impact of confounding information and noise using a two-stage regression technique borrowed from the instrumental variable literature. We also model the completeness of the concepts set and show that our debiasing method works when the concepts are not complete. Our synthetic and real-world experiments demonstrate the success of our method in removing biases and improving the ranking of the concepts in terms of their contribution to the explanation of the predictions.

Key facts. Cited by 32 papers in the map (data through 13 Oct 2026). First posted on arXiv 22 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 10; 2023: 11; 2024: 5; 2025: 3.

32 papers.

Sort:

By area:

  1. 2021Acquisition of Chess Knowledge in AlphaZerocited by 122
  2. 2022Concept Bottleneck Model with Additional Unsupervised Conceptscited by 79
  3. 2022Interactive Concept Bottleneck Modelscited by 79
  4. 2023Discover and Cure: Concept-aware Mitigation of Spurious Correlationcited by 71
  5. 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Modelscited by 64
  6. 2022Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlationcited by 59
  7. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 53
  8. 2024Incremental Residual Concept Bottleneck Modelscited by 43
  9. 2023Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZerocited by 42
  10. 2023Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlationcited by 25
  11. 2022Human-Centered Concept Explanations for Neural Networkscited by 23
  12. 2022Concept Gradient: Concept-based Interpretation Without Linear Assumptioncited by 20
20 more
  1. 2022Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Mediacited by 20
  2. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 18
  3. 2023Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounderscited by 17
  4. 2025If Concept Bottlenecks are the Question, are Foundation Models the Answer?cited by 15
  5. 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lenscited by 13
  6. 2022Adapting to Latent Subgroup Shifts via Concepts and Proxiescited by 12
  7. 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvementcited by 10
  8. 2024A survey on Concept-based Approaches For Model Improvementcited by 8
  9. 2021Local Explanation of Dialogue Response Generationcited by 7
  10. 2024Counterfactual Concept Bottleneck Modelscited by 7
  11. 2022Towards learning to explain with concept bottleneck models: mitigating information leakagecited by 6
  12. 2023Benchmarking and Enhancing Disentanglement in Concept-Residual Modelscited by 5
  13. 2024DiConStruct: Causal Concept-based Explanations through Black-Box Distillationcited by 5
  14. 2025An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotationscited by 5
  15. 2021Toward a Unified Framework for Debugging Concept-based Modelscited by 4
  16. 2022Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spacescited by 4
  17. 2023A Survey of Explainable AI in Deep Visual Modeling: Methods and Metricscited by 4
  18. 2023Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffscited by 4
  19. 2023Debiasing Multimodal Models via Causal Information Minimizationcited by 4
  20. 2023Estimating Treatment Effects in Continuous Time with Hidden Confounderscited by 3