Federated Multi-Task Learning for Competing Constraints.
Year: 2020
Type: preprint
Abstract: In addition to accuracy, fairness and robustness are two critical concerns for federated learning systems. In this work, we first identify that robustness to adversarial training-time attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general multi-task learning objective, and analyze the ability of the objective to achieve a favorable tradeoff between fairness and robustness. We develop a scalable solver for the objective and show that multi-task learning can enable more accurate, robust, and fair models relative to state-of-the-art baselines across a suite of federated datasets.
Source: arXiv (Cornell University)
Authors: Li Tian, Shengyuan Hu, Ahmad Beirami, Virginia Smith
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3112076925