Adaptive incentive for cross-silo federated learning: A multi-agent reinforcement learning approach
This addresses the challenge of dynamic environments and privacy concerns in federated learning for organizations like financial or medical entities, though it appears incremental as it builds on existing incentive work.
The paper tackles the problem of incentivizing organizations to contribute data in cross-silo federated learning by proposing an adaptive mechanism based on multi-agent reinforcement learning, which learns near-optimal strategies without private information and improves long-term payoffs for organizations.
Cross-silo federated learning (FL) is a typical FL that enables organizations(e.g., financial or medical entities) to train global models on isolated data. Reasonable incentive is key to encouraging organizations to contribute data. However, existing works on incentivizing cross-silo FL lack consideration of the environmental dynamics (e.g., precision of the trained global model and data owned by uncertain clients during the training processes). Moreover, most of them assume that organizations share private information, which is unrealistic. To overcome these limitations, we propose a novel adaptive mechanism for cross-silo FL, towards incentivizing organizations to contribute data to maximize their long-term payoffs in a real dynamic training environment. The mechanism is based on multi-agent reinforcement learning, which learns near-optimal data contribution strategy from the history of potential games without organizations' private information. Experiments demonstrate that our mechanism achieves adaptive incentive and effectively improves the long-term payoffs for organizations.