MAS: Towards Resource-Efficient Federated Multiple-Task Learning
This addresses resource efficiency for federated learning on edge devices, but it is incremental as it builds on existing FL methods with a novel coordination approach.
The paper tackles the problem of resource overload from multiple simultaneous federated learning tasks on edge devices by proposing MAS, a system that merges tasks into an all-in-one model and then splits them based on task affinities, resulting in a 2x reduction in training time and 40% reduction in energy consumption.
Federated learning (FL) is an emerging distributed machine learning method that empowers in-situ model training on decentralized edge devices. However, multiple simultaneous FL tasks could overload resource-constrained devices. In this work, we propose the first FL system to effectively coordinate and train multiple simultaneous FL tasks. We first formalize the problem of training simultaneous FL tasks. Then, we present our new approach, MAS (Merge and Split), to optimize the performance of training multiple simultaneous FL tasks. MAS starts by merging FL tasks into an all-in-one FL task with a multi-task architecture. After training for a few rounds, MAS splits the all-in-one FL task into two or more FL tasks by using the affinities among tasks measured during the all-in-one training. It then continues training each split of FL tasks based on model parameters from the all-in-one training. Extensive experiments demonstrate that MAS outperforms other methods while reducing training time by 2x and reducing energy consumption by 40%. We hope this work will inspire the community to further study and optimize training simultaneous FL tasks.