【第84期】FedBone：大规模多任务联邦学习

Seventy3: 用NotebookLM将论文生成播客，让大家跟着AI一起进步。

今天的主题是：

FedBone: Towards Large-Scale Federated Multi-Task Learning

Summary

The paper introduces FedBone, a novel federated multi-task learning framework designed for large-scale models and heterogeneous tasks. It employs split learning to distribute computation efficiently between a cloud server and resource-constrained edge clients. A gradient projection method addresses conflicts arising from heterogeneous tasks during model aggregation. FedBone incorporates privacy-preserving techniques and asynchronous optimization for robustness and scalability. Extensive experiments on benchmark and real-world ophthalmic datasets demonstrate its superior performance compared to existing methods.

原文链接：https://link.springer.com/article/10.1007/s11390-024-3639-x

https://arxiv.org/abs/2306.17465