A diversity-aware incentive mechanism for cross-silo federated learning with budget constraint

Federated learning (FL) relies on a sufficient number of clients to utilize their local data for model training, making the incentive mechanism a crucial component for its success. Given the significant impact of the training dataset on FL performance, we introduce two key metrics: the scale and diversity of the training data. These factors are vital for improving model accuracy. However, designing an incentive mechanism that accounts for both the scale and diversity of data in FL is a challenge task. To address this, we propose an auction-based method for multi-dimensional objectives, called the diversity-aware incentive mechanism (DAIM). We prove that the DAIM satisfies three important properties: truthfulness, individual rationality and budget feasibility. Under this mechanism, clients are incentivized to truthfully report the size, distribution and cost of their local datasets, with selected clients contributing all or part of their data to federated model training. Experimental results show that, especially when the budget is limited, DAIM outperforms existing methods that ignore data diversity, particularly when there is significant variation in dataset distributions across clients.