CoBo: Collaborative Learning via Bilevel Optimization
This addresses the problem of efficient client selection in collaborative learning for distributed datasets, offering a scalable solution with theoretical guarantees, though it appears incremental as it builds on existing optimization methods.
The paper tackles the challenge of identifying helpful clients in collaborative learning by modeling client-selection and model-training as a bilevel optimization problem, resulting in CoBo, which achieves 9.3% higher accuracy than popular personalization algorithms on a heterogeneous task with 80 clients.
Collaborative learning is an important tool to train multiple clients more effectively by enabling communication among clients. Identifying helpful clients, however, presents challenging and often introduces significant overhead. In this paper, we model client-selection and model-training as two interconnected optimization problems, proposing a novel bilevel optimization problem for collaborative learning. We introduce CoBo, a scalable and elastic, SGD-type alternating optimization algorithm that efficiently addresses these problem with theoretical convergence guarantees. Empirically, CoBo achieves superior performance, surpassing popular personalization algorithms by 9.3% in accuracy on a task with high heterogeneity, involving datasets distributed among 80 clients.