Backend
SplitReAlign: Partition-Aware Representation Realignment for Split Federated Unlearning
arXiv cs.CR0 views
arXiv:2611.25301v1 Announce Type: cross 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.
Source:https://arxiv.org/abs/2611.25301PreviousVerified Netlist-to-RTL Recovery with LLM AgentsNextBraid: Sybil-Resistant Decentralized Identity with Trustless Key Recovery and Non-Transferable Anonymous Credentials
Related posts
Shipping an LLM feature to production: a 6-step checklist from real client projects
0dev.to
Why I Built an Ad-Free, 4K Video Downloader in Next.js 14 & Python (And Killed Popups Forever)
0dev.to
Three Hundred of Our Trade Accounts Belonged to Companies That No Longer Existed
0dev.to
Title40-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
0dev.to
Title50-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
0dev.to

Practical: a webcam physiology lab that grades itself against a wrist count
0dev.to