A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC Maximization

Xinwen Zhang, Ali Payani, Myungjin Lee, Richard Souvenir, Hongchang Gao
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59601-59640, 2024.

Abstract

AUC maximization is an effective approach to address the imbalanced data classification problem in federated learning. In the past few years, a couple of federated AUC maximization approaches have been developed based on the minimax optimization. However, directly solving a minimax optimization problem to maximize the AUC score cannot achieve satisfactory performance. To address this issue, we propose to maximize AUC via optimizing a federated multi-level compositional minimax problem. Specifically, we develop a novel federated multi-level compositional minimax algorithm with rigorous theoretical guarantees to solve this new learning paradigm in both algorithmic design and theoretical analysis. To the best of our knowledge, this is the first work studying the multi-level minimax optimization problem. Additionally, extensive empirical evaluations confirm the efficacy of our proposed approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-zhang24aw, title = {A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep {AUC} Maximization}, author = {Zhang, Xinwen and Payani, Ali and Lee, Myungjin and Souvenir, Richard and Gao, Hongchang}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {59601--59640}, 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/zhang24aw/zhang24aw.pdf}, url = {https://proceedings.mlr.press/v235/zhang24aw.html}, abstract = {AUC maximization is an effective approach to address the imbalanced data classification problem in federated learning. In the past few years, a couple of federated AUC maximization approaches have been developed based on the minimax optimization. However, directly solving a minimax optimization problem to maximize the AUC score cannot achieve satisfactory performance. To address this issue, we propose to maximize AUC via optimizing a federated multi-level compositional minimax problem. Specifically, we develop a novel federated multi-level compositional minimax algorithm with rigorous theoretical guarantees to solve this new learning paradigm in both algorithmic design and theoretical analysis. To the best of our knowledge, this is the first work studying the multi-level minimax optimization problem. Additionally, extensive empirical evaluations confirm the efficacy of our proposed approach.} }
Endnote
%0 Conference Paper %T A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC Maximization %A Xinwen Zhang %A Ali Payani %A Myungjin Lee %A Richard Souvenir %A Hongchang Gao %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-zhang24aw %I PMLR %P 59601--59640 %U https://proceedings.mlr.press/v235/zhang24aw.html %V 235 %X AUC maximization is an effective approach to address the imbalanced data classification problem in federated learning. In the past few years, a couple of federated AUC maximization approaches have been developed based on the minimax optimization. However, directly solving a minimax optimization problem to maximize the AUC score cannot achieve satisfactory performance. To address this issue, we propose to maximize AUC via optimizing a federated multi-level compositional minimax problem. Specifically, we develop a novel federated multi-level compositional minimax algorithm with rigorous theoretical guarantees to solve this new learning paradigm in both algorithmic design and theoretical analysis. To the best of our knowledge, this is the first work studying the multi-level minimax optimization problem. Additionally, extensive empirical evaluations confirm the efficacy of our proposed approach.
APA
Zhang, X., Payani, A., Lee, M., Souvenir, R. & Gao, H.. (2024). A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC Maximization. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:59601-59640 Available from https://proceedings.mlr.press/v235/zhang24aw.html.

Related Material