Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Increasing Performance And Sample Efficiency With Model-agnostic Interactive Feature Attributions (2306.16431v1)

Published 28 Jun 2023 in cs.LG and cs.AI

Abstract: Model-agnostic feature attributions can provide local insights in complex ML models. If the explanation is correct, a domain expert can validate and trust the model's decision. However, if it contradicts the expert's knowledge, related work only corrects irrelevant features to improve the model. To allow for unlimited interaction, in this paper we provide model-agnostic implementations for two popular explanation methods (Occlusion and Shapley values) to enforce entirely different attributions in the complex model. For a particular set of samples, we use the corrected feature attributions to generate extra local data, which is used to retrain the model to have the right explanation for the samples. Through simulated and real data experiments on a variety of models we show how our proposed approach can significantly improve the model's performance only by augmenting its training dataset based on corrected explanations. Adding our interactive explanations to active learning settings increases the sample efficiency significantly and outperforms existing explanatory interactive strategies. Additionally we explore how a domain expert can provide feature attributions which are sufficiently correct to improve the model.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (22)
  1. Explanatory interactive machine learning. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pages 239–245, 2019.
  2. Making deep neural networks right for the right scientific reasons by interacting with their explanations. Nature Machine Intelligence, 2(8):476–486, 2020.
  3. Visualizing and understanding convolutional networks. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13, pages 818–833. Springer, 2014.
  4. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017.
  5. Burr Settles. Active learning literature survey. 2009.
  6. Axiomatic attribution for deep networks. In International conference on machine learning, pages 3319–3328. PMLR, 2017.
  7. From local explanations to global understanding with explainable ai for trees. Nature machine intelligence, 2(1):56–67, 2020.
  8. The many shapley values for model explanation. In International conference on machine learning, pages 9269–9278. PMLR, 2020.
  9. " 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.
  10. Right for the right reasons: Training differentiable models by constraining their explanations. arXiv preprint arXiv:1703.03717, 2017.
  11. Using “annotator rationales” to improve machine learning for text categorization. In Human language technologies 2007: The conference of the North American chapter of the association for computational linguistics; proceedings of the main conference, pages 260–267, 2007.
  12. The constrained weight space svm: learning with ranked features. In Proceedings of the 28th International Conference on International Conference on Machine Learning, pages 865–872, 2011.
  13. Principles of explanatory debugging to personalize interactive machine learning. In Proceedings of the 20th international conference on intelligent user interfaces, pages 126–137, 2015.
  14. Leveraging explanations in interactive machine learning: An overview. arXiv preprint arXiv:2207.14526, 2022.
  15. A typology for exploring the mitigation of shortcut behaviour. Nature Machine Intelligence, pages 1–12, 2023.
  16. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nature biomedical engineering, 2(10):749–760, 2018.
  17. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.
  18. Hedonic housing prices and the demand for clean air. Journal of environmental economics and management, 5(1):81–102, 1978.
  19. Counterfactual explanations and algorithmic recourses for machine learning: a review. arXiv preprint arXiv:2010.10596, 2020.
  20. Explaining by removing: A unified framework for model explanation. The Journal of Machine Learning Research, 22(1):9477–9566, 2021.
  21. Sanity checks for saliency metrics. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 6021–6029, 2020.
  22. How can i choose an explainer? an application-grounded evaluation of post-hoc explanations. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, pages 805–815, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Joran Michiels (2 papers)
  2. Maarten De Vos (41 papers)
  3. Johan Suykens (11 papers)