Unravelling in Collaborative Learning
Capitaine, Aymeric Boursier, Etienne Scheid, Antoine Moulines, Eric Jordan, Michael I. El-Mhamdi, El-Mahdi Durmus, Alain
Capitaine, Aymeric
Boursier, Etienne
Scheid, Antoine
Moulines, Eric
Jordan, Michael I.
El-Mhamdi, El-Mahdi
Durmus, Alain
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2024
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Collaborative learning offers a promising avenue for leveraging decentralized data. However, collaboration in groups of strategic learners is not a given. In this work, we consider strategic agents who wish to train a model together but have sampling distributions of different quality. The collaboration is organized by a benevolent aggregator who gathers samples so as to maximize total welfare, but is unaware of data quality. This setting allows us to shed light on the deleterious effect of adverse selection in collaborative learning. More precisely, we demonstrate that when data quality indices are private, the coalition may undergo a phenomenon known as unravelling, wherein it shrinks up to the point that it becomes empty or solely comprised of the worst agent. We show how this issue can be addressed without making use of external transfers, by proposing a novel method inspired by probabilistic verification. This approach makes the grand coalition a Nash equilibrium with high probability despite information asymmetry, thereby breaking unravelling.
Citation
A. Capitaine et al., “Unravelling in Collaborative Learning,” Adv Neural Inf Process Syst, vol. 37, pp. 97231–97260, Dec. 2024.
Source
Advances in Neural Information Processing Systems (NeurIPS 2024)
Conference
Keywords
Collaborative learning, Strategic agents, Adverse selection, Information asymmetry, Probabilistic verification
Subjects
Source
Publisher
NEURIPS