English(EN) When Forgotten Facts Return: Relearning-Aware Unlearning of Knowledge Graph Embeddings via Tangent Kernels

新的KAU方法解决了知识图谱嵌入中的重学问题

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了一种名为核预期遗忘（KAU）的新方法，以解决在更新后知识图谱嵌入中遗忘的事实重新出现的问题。KAU利用切线核来模拟持续训练如何逆转遗忘过程，特别是在遗忘的事实和新事实共享底层参数时。该方法旨在指导编辑，最大限度地减少未来训练的影响，与现有方法相比，在保持效用的同时显著减少了事实泄露。 AI

影响这项研究可以提高知识图谱嵌入在抵抗不受欢迎的数据恢复方面的鲁棒性和安全性。

排序理由该集群包含一篇详细介绍知识图谱嵌入新方法的 ist 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: 4 / 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知识图谱嵌入新方法的 ist 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, other; 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) · Parnian Fazel, Mohammad M Maheri, Hamed Haddadi · 2026-10-23 04:00

When Forgotten Facts Return: Relearning-Aware Unlearning of Knowledge Graph Embeddings via Tangent Kernels

arXiv:2610.31075v1 Announce Type: new Abstract: Approximate unlearning answers a deletion request on a knowledge-graph embedding by editing entity embeddings instead of retraining from scratch. These embeddings keep being updated as new facts arrive. Under this ordinary continued…

本文如何被排名

报道来源 [1]

When Forgotten Facts Return: Relearning-Aware Unlearning of Knowledge Graph Embeddings via Tangent Kernels

相关实体

相关话题