Explain Temporal Black-Box Models via Functional Decomposition

Linxiao Yang, Yunze Tong, Xinyue Gu, Liang Sun
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56448-56464, 2024.

Abstract

How to explain temporal models is a significant challenge due to the inherent characteristics of time series data, notably the strong temporal dependencies and interactions between observations. Unlike ordinary tabular data, data at different time steps in time series usually interact dynamically, forming influential patterns that shape the model’s predictions, rather than only acting in isolation. Existing explanatory approaches for time series often overlook these crucial temporal interactions by treating time steps as separate entities, leading to a superficial understanding of model behavior. To address this challenge, we introduce FDTempExplainer, an innovative model-agnostic explanation method based on functional decomposition, tailored to unravel the complex interplay within black-box time series models. Our approach disentangles the individual contributions from each time step, as well as the aggregated influence of their interactions, in a rigorous framework. FDTempExplainer accurately measures the strength of interactions, yielding insights that surpass those from baseline models. We demonstrate the effectiveness of our approach in a wide range of time series applications, including anomaly detection, classification, and forecasting, showing its superior performance to the state-of-the-art algorithms.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-yang24y, title = {Explain Temporal Black-Box Models via Functional Decomposition}, author = {Yang, Linxiao and Tong, Yunze and Gu, Xinyue and Sun, Liang}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {56448--56464}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/yang24y/yang24y.pdf}, url = {https://proceedings.mlr.press/v235/yang24y.html}, abstract = {How to explain temporal models is a significant challenge due to the inherent characteristics of time series data, notably the strong temporal dependencies and interactions between observations. Unlike ordinary tabular data, data at different time steps in time series usually interact dynamically, forming influential patterns that shape the model’s predictions, rather than only acting in isolation. Existing explanatory approaches for time series often overlook these crucial temporal interactions by treating time steps as separate entities, leading to a superficial understanding of model behavior. To address this challenge, we introduce FDTempExplainer, an innovative model-agnostic explanation method based on functional decomposition, tailored to unravel the complex interplay within black-box time series models. Our approach disentangles the individual contributions from each time step, as well as the aggregated influence of their interactions, in a rigorous framework. FDTempExplainer accurately measures the strength of interactions, yielding insights that surpass those from baseline models. We demonstrate the effectiveness of our approach in a wide range of time series applications, including anomaly detection, classification, and forecasting, showing its superior performance to the state-of-the-art algorithms.} }
Endnote
%0 Conference Paper %T Explain Temporal Black-Box Models via Functional Decomposition %A Linxiao Yang %A Yunze Tong %A Xinyue Gu %A Liang Sun %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-yang24y %I PMLR %P 56448--56464 %U https://proceedings.mlr.press/v235/yang24y.html %V 235 %X How to explain temporal models is a significant challenge due to the inherent characteristics of time series data, notably the strong temporal dependencies and interactions between observations. Unlike ordinary tabular data, data at different time steps in time series usually interact dynamically, forming influential patterns that shape the model’s predictions, rather than only acting in isolation. Existing explanatory approaches for time series often overlook these crucial temporal interactions by treating time steps as separate entities, leading to a superficial understanding of model behavior. To address this challenge, we introduce FDTempExplainer, an innovative model-agnostic explanation method based on functional decomposition, tailored to unravel the complex interplay within black-box time series models. Our approach disentangles the individual contributions from each time step, as well as the aggregated influence of their interactions, in a rigorous framework. FDTempExplainer accurately measures the strength of interactions, yielding insights that surpass those from baseline models. We demonstrate the effectiveness of our approach in a wide range of time series applications, including anomaly detection, classification, and forecasting, showing its superior performance to the state-of-the-art algorithms.
APA
Yang, L., Tong, Y., Gu, X. & Sun, L.. (2024). Explain Temporal Black-Box Models via Functional Decomposition. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:56448-56464 Available from https://proceedings.mlr.press/v235/yang24y.html.

Related Material