PulseAugur
中
实时 08:58:13
English(EN) SplitReAlign: Partition-Aware Representation Realignment for Split Federated Unlearning

新框架SplitReAlign增强了联邦遗忘功能,可针对性地移除知识

研究人员推出了一种新颖的拆分联邦遗忘框架SplitReAlign。该方法解决了在分布式神经网络中移除特定知识的挑战,同时即使在不对称更新约束下也能保持整体效用。SplitReAlign通过创建由共享语义锚点协调的独特表示子空间来实现遗忘信息的定向重新对齐。在CIFAR-10和CIFAR-100数据集上的实验表明,SplitReAlign在各种设置下均取得了最接近重新训练的结果,其中仅服务器(Server-only)方法在更新受限的情况下尤其有效。 AI

影响 这项研究通过实现对特定数据的更精确移除而不损害整体模型性能,有望提高分布式环境中训练AI模型的效率和安全性。

排序理由 该集群包含一篇详细介绍联邦遗忘新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新框架SplitReAlign增强了联邦遗忘功能,可针对性地移除知识

本文如何被排名

Signal score
19 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍联邦遗忘新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Jia Chen, Yecheng Lv, Xinrong Hu, Jun Bai ·

    SplitReAlign: 面向拆分联邦式遗忘的、感知拆分的表征重对齐

    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 for…