FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
It addresses the free-rider dilemma for federated learning systems, making mechanisms more robust in practice, though it appears incremental as it builds on prior work by adding truthfulness.
The paper tackles the problem of free-riding in federated learning, where agents can cheat by providing false information, and proposes FACT, a truthful mechanism that eliminates free-riding and reduces agent loss by over 4x.
Standard federated learning (FL) approaches are vulnerable to the free-rider dilemma: participating agents can contribute little to nothing yet receive a well-trained aggregated model. While prior mechanisms attempt to solve the free-rider dilemma, none have addressed the issue of truthfulness. In practice, adversarial agents can provide false information to the server in order to cheat its way out of contributing to federated training. In an effort to make free-riding-averse federated mechanisms truthful, and consequently less prone to breaking down in practice, we propose FACT. FACT is the first federated mechanism that: (1) eliminates federated free riding by using a penalty system, (2) ensures agents provide truthful information by creating a competitive environment, and (3) encourages agent participation by offering better performance than training alone. Empirically, FACT avoids free-riding when agents are untruthful, and reduces agent loss by over 4x.