Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
149 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

An Axiomatic Approach to Model-Agnostic Concept Explanations (2401.06890v1)

Published 12 Jan 2024 in cs.LG

Abstract: Concept explanation is a popular approach for examining how human-interpretable concepts impact the predictions of a model. However, most existing methods for concept explanations are tailored to specific models. To address this issue, this paper focuses on model-agnostic measures. Specifically, we propose an approach to concept explanations that satisfy three natural axioms: linearity, recursivity, and similarity. We then establish connections with previous concept explanation methods, offering insight into their varying semantic meanings. Experimentally, we demonstrate the utility of the new method by applying it in different scenarios: for model selection, optimizer selection, and model improvement using a kind of prompt editing for zero-shot vision LLMs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (30)
  1. Concept gradient: Concept-based interpretation without linear assumption. arXiv preprint arXiv:2208.14966, 2022.
  2. Concept-level debugging of part-prototype networks. arXiv preprint arXiv:2205.15769, 2022.
  3. This looks like that: deep learning for interpretable image recognition. Advances in neural information processing systems, 32, 2019.
  4. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416, 2022.
  5. Imre Csiszár. Axiomatic characterizations of information measures. Entropy, 10(3):261–273, 2008.
  6. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  7. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  8. Concept embedding models: Beyond the accuracy-explainability trade-off. Advances in Neural Information Processing Systems, 35:21400–21413, 2022.
  9. Describing objects by their attributes. In 2009 IEEE conference on computer vision and pattern recognition, pages 1778–1785. IEEE, 2009.
  10. Towards automatic concept-based explanations. Advances in Neural Information Processing Systems, 32, 2019.
  11. Which explanation should I choose? a function approximation perspective to characterizing post hoc explanations. arXiv preprint arXiv:2206.01254, 2022.
  12. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  13. Model-agnostic counterfactual explanations for consequential decisions. In International Conference on Artificial Intelligence and Statistics, pages 895–905. PMLR, 2020.
  14. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV). In International conference on machine learning, pages 2668–2677. PMLR, 2018.
  15. Understanding black-box predictions via influence functions. In International conference on machine learning, pages 1885–1894. PMLR, 2017.
  16. Concept bottleneck models. In International Conference on Machine Learning, pages 5338–5348. PMLR, 2020.
  17. On the accuracy of influence functions for measuring group effects. Advances in neural information processing systems, 32, 2019.
  18. The disagreement problem in explainable machine learning: A practitioner’s perspective. arXiv preprint arXiv:2202.01602, 2022.
  19. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597, 2023.
  20. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017.
  21. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.
  22. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. PMLR, 2021.
  23. ” why should I trust you?” explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144, 2016.
  24. Anchors: High-precision model-agnostic explanations. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 2018.
  25. Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.
  26. Axiomatic attribution for deep networks. In International conference on machine learning, pages 3319–3328. PMLR, 2017.
  27. Counterfactual explanations without opening the black box: Automated decisions and the gdpr. Harv. JL & Tech., 31:841, 2017.
  28. On completeness-aware concept-based explanations in deep neural networks. Advances in Neural Information Processing Systems, 33:20554–20565, 2020.
  29. Post-hoc concept bottleneck models. In International Conference on Learning Representations, 2023.
  30. Towards theoretically understanding why sgd generalizes better than adam in deep learning. Advances in Neural Information Processing Systems, 33:21285–21296, 2020.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now