English(EN) Privacy Preserving Gossip Learning

新的去中心化学习算法通过流言协议增强隐私保护

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了一种新颖的去中心化学习算法，旨在保护隐私。该方法允许代理从个体私有样本中学习，同时顺序更新共享模型。该算法基于“不遗忘调优”（Tuning without Forgetting, TwF）技术来保持先前学习到的映射，并在特定条件下为学习者提供不可区分性保证。对于教师代理，通过构建一个最小-最大最优控制问题来平衡隐私和性能，同时使用私有推-加流言协议（private push-sum gossip protocol）聚合受保护代理的贡献。该方法已被证明在去中心化流言和分布式投影方面都能实现几何收敛。 AI

影响引入了一种新的安全去中心化学习方法，可能促进AI模型训练中更私有的数据协作。

排序理由该集群包含一篇详细介绍新颖的去中心化隐私保护学习算法的研究论文。[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 →

本文如何被排名

Signal score: 11 / 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新颖的去中心化隐私保护学习算法的研究论文。[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, safety; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Erkan Bayram, Mohamed-Ali Belabbas, Tamer Ba\c{s}ar · 2026-09-15 04:00

隐私保护的流言学习

arXiv:2609.14778v1 Announce Type: new Abstract: We propose a decentralized privacy-preserving learning algorithm in which each agent holds a single private sample and a shared model. Samples are learned sequentially, and each update must preserve the endpoint mappings at previous…

本文如何被排名

报道来源 [1]

隐私保护的流言学习

相关实体

相关话题