Explaining Drift using Shapley Values (2401.09756v1)
Abstract: Machine learning models often deteriorate in their performance when they are used to predict the outcomes over data on which they were not trained. These scenarios can often arise in real world when the distribution of data changes gradually or abruptly due to major events like a pandemic. There have been many attempts in machine learning research to come up with techniques that are resilient to such Concept drifts. However, there is no principled framework to identify the drivers behind the drift in model performance. In this paper, we propose a novel framework - DBShap that uses Shapley values to identify the main contributors of the drift and quantify their respective contributions. The proposed framework not only quantifies the importance of individual features in driving the drift but also includes the change in the underlying relation between the input and output as a possible driver. The explanation provided by DBShap can be used to understand the root cause behind the drift and use it to make the model resilient to the drift.
- A Framework for Explainable Concept Drift Detection in Process Mining. In Business Process Management, Artem Polyvyanyy, Moe Thandar Wynn, Amy Van Looy, and Manfred Reichert (Eds.). Springer International Publishing, Cham, 400–416.
- Cesare Alippi and Manuel Roveri. 2008. Just-in-Time Adaptive Classifiers—Part I: Detecting Nonstationary Changes. IEEE Transactions on Neural Networks 19, 7 (2008), 1145–1153. https://doi.org/10.1109/TNN.2008.2000082
- An Information-Theoretic Approach to Detecting Changes in MultiDimensional Data Streams. Interfaces (01 2006).
- A Survey on Concept Drift Adaptation. ACM Comput. Surv. 46, 4, Article 44 (mar 2014), 37 pages. https://doi.org/10.1145/2523813
- A General Framework for Mining Concept-Drifting Data Streams with Skewed Distributions. https://doi.org/10.1137/1.9781611972771.1
- Ensemble learning for data stream analysis: A survey. Information Fusion 37 (2017), 132–156. https://doi.org/10.1016/j.inffus.2017.02.004
- Using multiple windows to track concept drift. Intell. Data Anal. 8 (03 2004), 29–59. https://doi.org/10.3233/IDA-2004-8103
- Learning under Concept Drift: A Review. IEEE Transactions on Knowledge and Data Engineering (2018), 1–1. https://doi.org/10.1109/tkde.2018.2876857
- Scott M Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf
- A survey on data preprocessing for data stream mining: Current status and future directions. Neurocomputing 239 (2017), 39–57. https://doi.org/10.1016/j.neucom.2017.01.078
- Marcos Salganicoff. 1993. Density-Adaptive Learning and Forgetting. In Proceedings of the Tenth International Conference on International Conference on Machine Learning (Amherst, MA, USA) (ICML’93). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 276–283.
- Mukund Sundararajan and Amir Najmi. 2020. The Many Shapley Values for Model Explanation. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daumé III and Aarti Singh (Eds.). PMLR, 9269–9278. https://proceedings.mlr.press/v119/sundararajan20b.html
- Gerhard Widmer and Miroslav Kubat. 1996. Learning in the presence of concept drift and hidden contexts. Machine Learning 23, 1 (1996), 69–101. https://doi.org/10.1007/BF00116900