Extracting Rare Dependence Patterns via Adaptive Sample Reweighting

Yiqing Li, Yewei Xia, Xiaofei Wang, Zhengming Chen, Liuhua Peng, Mingming Gong, Kun Zhang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36365-36399, 2025.

Abstract

Discovering dependence patterns between variables from observational data is a fundamental issue in data analysis. However, existing testing methods often fail to detect subtle yet critical patterns that occur within small regions of the data distribution–patterns we term rare dependence. These rare dependencies obscure the true underlying dependence structure in variables, particularly in causal discovery tasks. To address this issue, we propose a novel testing method that combines kernel-based (conditional) independence testing with adaptive sample importance reweighting. By learning and assigning higher importance weights to data points exhibiting significant dependence, our method amplifies the patterns and can detect them successfully. Theoretically, we analyze the asymptotic distributions of the statistics in this method and show the uniform bound of the learning scheme. Furthermore, we integrate our tests into the PC algorithm, a constraint-based approach for causal discovery, equipping it to uncover causal relationships even in the presence of rare dependence. Empirical evaluation of synthetic and real-world datasets comprehensively demonstrates the efficacy of our method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-li25da, title = {Extracting Rare Dependence Patterns via Adaptive Sample Reweighting}, author = {Li, Yiqing and Xia, Yewei and Wang, Xiaofei and Chen, Zhengming and Peng, Liuhua and Gong, Mingming and Zhang, Kun}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {36365--36399}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/li25da/li25da.pdf}, url = {https://proceedings.mlr.press/v267/li25da.html}, abstract = {Discovering dependence patterns between variables from observational data is a fundamental issue in data analysis. However, existing testing methods often fail to detect subtle yet critical patterns that occur within small regions of the data distribution–patterns we term rare dependence. These rare dependencies obscure the true underlying dependence structure in variables, particularly in causal discovery tasks. To address this issue, we propose a novel testing method that combines kernel-based (conditional) independence testing with adaptive sample importance reweighting. By learning and assigning higher importance weights to data points exhibiting significant dependence, our method amplifies the patterns and can detect them successfully. Theoretically, we analyze the asymptotic distributions of the statistics in this method and show the uniform bound of the learning scheme. Furthermore, we integrate our tests into the PC algorithm, a constraint-based approach for causal discovery, equipping it to uncover causal relationships even in the presence of rare dependence. Empirical evaluation of synthetic and real-world datasets comprehensively demonstrates the efficacy of our method.} }
Endnote
%0 Conference Paper %T Extracting Rare Dependence Patterns via Adaptive Sample Reweighting %A Yiqing Li %A Yewei Xia %A Xiaofei Wang %A Zhengming Chen %A Liuhua Peng %A Mingming Gong %A Kun Zhang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-li25da %I PMLR %P 36365--36399 %U https://proceedings.mlr.press/v267/li25da.html %V 267 %X Discovering dependence patterns between variables from observational data is a fundamental issue in data analysis. However, existing testing methods often fail to detect subtle yet critical patterns that occur within small regions of the data distribution–patterns we term rare dependence. These rare dependencies obscure the true underlying dependence structure in variables, particularly in causal discovery tasks. To address this issue, we propose a novel testing method that combines kernel-based (conditional) independence testing with adaptive sample importance reweighting. By learning and assigning higher importance weights to data points exhibiting significant dependence, our method amplifies the patterns and can detect them successfully. Theoretically, we analyze the asymptotic distributions of the statistics in this method and show the uniform bound of the learning scheme. Furthermore, we integrate our tests into the PC algorithm, a constraint-based approach for causal discovery, equipping it to uncover causal relationships even in the presence of rare dependence. Empirical evaluation of synthetic and real-world datasets comprehensively demonstrates the efficacy of our method.
APA
Li, Y., Xia, Y., Wang, X., Chen, Z., Peng, L., Gong, M. & Zhang, K.. (2025). Extracting Rare Dependence Patterns via Adaptive Sample Reweighting. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:36365-36399 Available from https://proceedings.mlr.press/v267/li25da.html.

Related Material