Efficient and Effective Federated Unlearning via Adaptive Data Partitioning
This paper first establishes inter-shard relationships via a personalized aggregation mechanism, which significantly alleviates the model accuracy degradation caused by disjoint sharding and non-IID data, while still ensuring confined unlearning overhead.
Zhi-Gang Wang, Jia-Hao Li, Ning Wang et al.
· IEEE Transactions on Knowled... · 0 citations