Fair yet Asymptotically Equal Collaborative Learning

Xiaoqiang Lin, Xinyi Xu, See-Kiong Ng, Chuan-Sheng Foo, Bryan Kian Hsiang Low
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21223-21259, 2023.

Abstract

In collaborative learning with streaming data, nodes (e.g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data. For the more resourceful nodes to be willing to share their model updates, they need to be fairly incentivized. This paper explores an incentive design that guarantees fairness so that nodes receive rewards commensurate to their contributions. Our approach leverages an explore-then-exploit formulation to estimate the nodes’ contributions (i.e., exploration) for realizing our theoretically guaranteed fair incentives (i.e., exploitation). However, we observe a "rich get richer" phenomenon arising from the existing approaches to guarantee fairness and it discourages the participation of the less resourceful nodes. To remedy this, we additionally preserve asymptotic equality, i.e., less resourceful nodes achieve equal performance eventually to the more resourceful/“rich” nodes. We empirically demonstrate in two settings with real-world streaming data: federated online incremental learning and federated reinforcement learning, that our proposed approach outperforms existing baselines in fairness and learning performance while remaining competitive in preserving equality.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-lin23l, title = {Fair yet Asymptotically Equal Collaborative Learning}, author = {Lin, Xiaoqiang and Xu, Xinyi and Ng, See-Kiong and Foo, Chuan-Sheng and Low, Bryan Kian Hsiang}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {21223--21259}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/lin23l/lin23l.pdf}, url = {https://proceedings.mlr.press/v202/lin23l.html}, abstract = {In collaborative learning with streaming data, nodes (e.g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data. For the more resourceful nodes to be willing to share their model updates, they need to be fairly incentivized. This paper explores an incentive design that guarantees fairness so that nodes receive rewards commensurate to their contributions. Our approach leverages an explore-then-exploit formulation to estimate the nodes’ contributions (i.e., exploration) for realizing our theoretically guaranteed fair incentives (i.e., exploitation). However, we observe a "rich get richer" phenomenon arising from the existing approaches to guarantee fairness and it discourages the participation of the less resourceful nodes. To remedy this, we additionally preserve asymptotic equality, i.e., less resourceful nodes achieve equal performance eventually to the more resourceful/“rich” nodes. We empirically demonstrate in two settings with real-world streaming data: federated online incremental learning and federated reinforcement learning, that our proposed approach outperforms existing baselines in fairness and learning performance while remaining competitive in preserving equality.} }
Endnote
%0 Conference Paper %T Fair yet Asymptotically Equal Collaborative Learning %A Xiaoqiang Lin %A Xinyi Xu %A See-Kiong Ng %A Chuan-Sheng Foo %A Bryan Kian Hsiang Low %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-lin23l %I PMLR %P 21223--21259 %U https://proceedings.mlr.press/v202/lin23l.html %V 202 %X In collaborative learning with streaming data, nodes (e.g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data. For the more resourceful nodes to be willing to share their model updates, they need to be fairly incentivized. This paper explores an incentive design that guarantees fairness so that nodes receive rewards commensurate to their contributions. Our approach leverages an explore-then-exploit formulation to estimate the nodes’ contributions (i.e., exploration) for realizing our theoretically guaranteed fair incentives (i.e., exploitation). However, we observe a "rich get richer" phenomenon arising from the existing approaches to guarantee fairness and it discourages the participation of the less resourceful nodes. To remedy this, we additionally preserve asymptotic equality, i.e., less resourceful nodes achieve equal performance eventually to the more resourceful/“rich” nodes. We empirically demonstrate in two settings with real-world streaming data: federated online incremental learning and federated reinforcement learning, that our proposed approach outperforms existing baselines in fairness and learning performance while remaining competitive in preserving equality.
APA
Lin, X., Xu, X., Ng, S., Foo, C. & Low, B.K.H.. (2023). Fair yet Asymptotically Equal Collaborative Learning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:21223-21259 Available from https://proceedings.mlr.press/v202/lin23l.html.

Related Material