arXiv:2611.25301v1 Announce Type: new
Abstract: Split federated learning (SFL) distributes neural networks across clients and a server, coupling class-specific knowledge across their representations. This coupling complicates split federated unlearning (SFU), where class-wise forgetting must remove target knowledge while preserving retained utility under heterogeneous representation spaces and asymmetric update constraints. We propose SplitReAlign, a partition-aware representation realignment framework for class-wise SFU. It constructs endpoint-specific discriminative subspaces coordinated through a shared semantic anchor, selectively realigning forgotten representations while penalizing changes outside the active subspaces. To accommodate asymmetric update constraints, SplitReAlign leverages gradients through frozen servers for Client-only updates and fixed client-feature statistics for Server-only guidance, while Joint updates optimize both partitions. Experiments on CIFAR-10 and CIFAR-100 under heterogeneous client distributions demonstrate that SplitReAlign achieves the lowest average gap to retraining among all compared methods across six settings. Notably, Server-only achieves the closest agreement with retraining on both datasets, highlighting the effectiveness of partition-aware guidance under restricted updates.
Trending
- The 23 Best Early Black Friday Deals: Our Ultimate Picks (2026)
- SplitReAlign: Partition-Aware Representation Realignment for Split Federated Unlearning
- Efficient Hybrid LLM Serving with Transparent Cache Management and Layer-Wise Streaming
- [2611.25300] Federated Learning of Car Aerodynamics Surrogates with Spectral Optimizers
- Deterministic Temporal Embedding for Calcium Imaging Trace Extraction
- Valve says it might have to raise the price of supply-limited Steam Machines
- Cross-Question Reliable Reinforcement Learning
- Don’t Bring Jensen Back | WIRED
