Fair yet Asymptotically Equal Collaborative Learning

TL;DR

This paper proposes a fair and asymptotically equal collaborative learning framework for streaming data, incentivizing nodes based on contribution while ensuring less resourceful nodes eventually achieve comparable performance.

Contribution

It introduces an explore-then-exploit incentive mechanism that guarantees fairness and asymptotic equality in collaborative streaming learning settings.

Findings

Outperforms existing methods in fairness and learning performance.

Maintains asymptotic equality among nodes.

Effective in federated online incremental and reinforcement learning.

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.