Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

Self-Interpretable Time Series Prediction with Counterfactual Explanations (2306.06024v3)

Published 9 Jun 2023 in cs.LG

Abstract: Interpretable time series prediction is crucial for safety-critical areas such as healthcare and autonomous driving. Most existing methods focus on interpreting predictions by assigning important scores to segments of time series. In this paper, we take a different and more challenging route and aim at developing a self-interpretable model, dubbed Counterfactual Time Series (CounTS), which generates counterfactual and actionable explanations for time series predictions. Specifically, we formalize the problem of time series counterfactual explanations, establish associated evaluation protocols, and propose a variational Bayesian deep learning model equipped with counterfactual inference capability of time series abduction, action, and prediction. Compared with state-of-the-art baselines, our self-interpretable model can generate better counterfactual explanations while maintaining comparable prediction accuracy.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Learning to explain: An information-theoretic perspective on model interpretation. In International Conference on Machine Learning, pp. 883–892. PMLR, 2018.
  2. Racial/ethnic differences in sleep disturbances: The multi-ethnic study of atherosclerosis (mesa). Sleep, 38, 11 2014. doi: 10.5665/sleep.4732.
  3. Appendicular bone density and age predict hip fracture in women. JAMA, 263(5):665–668, 1990.
  4. Causal and interpretable rules for time series analysis. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp.  2764–2772, 2021.
  5. Zero-shot recommender systems. In ICLR Workshop on Deep Generative Models for Highly Structured Data, 2022.
  6. Towards automatic concept-based explanations. Advances in Neural Information Processing Systems, 32, 2019.
  7. Counterfactual visual explanations. In International Conference on Machine Learning, pp. 2376–2384. PMLR, 2019.
  8. Correcting exposure bias for link recommendation. In International Conference on Machine Learning, pp. 3953–3963. PMLR, 2021.
  9. Uncertainty-aware attention for reliable interpretation and prediction. In Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., and Garnett, R. (eds.), Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., 2018.
  10. Recurrent poisson process unit for speech recognition. In AAAI, volume 33, pp.  6538–6545, 2019.
  11. Domain adaptation for time series forecasting via attention sharing. In International Conference on Machine Learning, pp. 10280–10297. PMLR, 2022.
  12. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  13. Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4):1748–1764, 2021.
  14. Orphicx: A causality-inspired latent variable model for interpreting graph neural networks. In CVPR, 2022.
  15. Causal effect inference with deep latent-variable models. Advances in neural information processing systems, 30, 2017.
  16. A unified approach to interpreting model predictions. In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (eds.), Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017a.
  17. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017b.
  18. Adversarial attacks are reversible with natural supervision. In ICCV, 2021a.
  19. Generative interventions for causal learning. In CVPR, 2021b.
  20. Training-free uncertainty estimation for neural networks. In AAAI, 2022.
  21. Model agnostic multilevel explanations. Advances in neural information processing systems, 33:5968–5979, 2020.
  22. Countergan: Generating counterfactuals for real-time recourse and interpretability using residual gans. In Cussens, J. and Zhang, K. (eds.), Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, volume 180 of Proceedings of Machine Learning Research, pp.  1488–1497. PMLR, 01–05 Aug 2022.
  23. Two birds with one stone: Series saliency for accurate and interpretable multivariate time series forecasting. In IJCAI, pp.  2884–2891, 2021.
  24. Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32, pp. 8024–8035. Curran Associates, Inc., 2019.
  25. Deep structural causal models for tractable counterfactual inference. Advances in Neural Information Processing Systems, 33:857–869, 2020.
  26. Pearl, J. Causality. Cambridge University Press, 2 edition, 2009.
  27. Model agnostic supervised local explanations. Advances in neural information processing systems, 31, 2018.
  28. Regularizing black-box models for improved interpretability. Advances in Neural Information Processing Systems, 33:10526–10536, 2020.
  29. The sleep heart health study: Design, rationale, and methods. Sleep, 20:1077–85, 01 1998. doi: 10.1093/sleep/20.12.1077.
  30. The sleep heart health study: design, rationale, and methods. Sleep, 20(12):1077–1085, 1997.
  31. Limref: Local interpretable model agnostic rule-based explanations for forecasting, with an application to electricity smart meter data. arXiv preprint arXiv:2202.07766, 2022.
  32. ”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, pp.  1135–1144, 2016.
  33. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pp.  618–626, 2017.
  34. Learning important features through propagating activation differences. In International conference on machine learning, pp. 3145–3153. PMLR, 2017.
  35. Sleep-disordered breathing and cognition in older women. Journal of the American Geriatrics Society, 56(1):45–50, 2008.
  36. Axiomatic attribution for deep networks. In International conference on machine learning, pp. 3319–3328. PMLR, 2017.
  37. What went wrong and when? instance-wise feature importance for time-series black-box models. In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H. (eds.), Advances in Neural Information Processing Systems, volume 33, pp.  799–809. Curran Associates, Inc., 2020.
  38. Counterfactual explanations without opening the black box: Automated decisions and the gdpr. Harv. JL & Tech., 31:841, 2017a.
  39. Counterfactual explanations without opening the black box: Automated decisions and the gdpr. Cybersecurity, 2017b.
  40. Wang, H. Bayesian Deep Learning for Integrated Intelligence: Bridging the Gap between Perception and Inference. PhD thesis, Hong Kong University of Science and Technology, 2017.
  41. Towards bayesian deep learning: A framework and some existing methods. TDKE, 28(12):3395–3408, 2016.
  42. A survey on bayesian deep learning. CSUR, 53(5):1–37, 2020.
  43. Collaborative deep learning for recommender systems. In KDD, pp.  1235–1244, 2015.
  44. Bidirectional inference networks: A class of deep bayesian networks for health profiling. In AAAI, volume 33, pp.  766–773, 2019a.
  45. Bias also matters: Bias attribution for deep neural network explanation. In International Conference on Machine Learning, pp. 6659–6667. PMLR, 2019b.
  46. Causal discovery from incomplete data: A deep learning approach. 2020.
  47. Learning deep attribution priors based on prior knowledge. Advances in Neural Information Processing Systems, 33:14034–14045, 2020.
  48. Artificial intelligence-enabled detection and assessment of parkinson’s disease using nocturnal breathing signals. Nature medicine, 28(10):2207–2215, 2022.
  49. The national sleep research resource: towards a sleep data commons. JAMA, 25(10):1351–1358, 2018a.
  50. The national sleep research resource: Towards a sleep data commons. Journal of the American Medical Informatics Association, pp. 572–572, 08 2018b. doi: 10.1145/3233547.3233725.
  51. Assessment of medication self-administration using artificial intelligence. Nature medicine, 27(4):727–735, 2021.
Citations (8)
View on Semantic Scholar

Summary

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

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