新方法可合并神经网络，减少模型宽度扩展

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

研究人员开发了一种新的预训练神经网络合并方法，该方法减少了对模型大幅度加宽的需求。这种基于倒数正交性的技术鼓励模型计算在合并网络中共存，即使在较小的宽度扩展下也能促进线性模式连接（LMC）。该方法已成功地合并了在不同数据分布上训练的模型，而传统的权重匹配方法在此类情况下会失效，并且合并后的预测结果与原始模型的logit集成结果非常接近。 AI

影响这项研究可能带来更高效的模型合并技术，从而降低计算成本，并能更好地利用多样化的预训练模型。

排序理由该集群包含一篇学术论文，详细介绍了一种新的预训练模型合并方法。[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: 34 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了一种新的预训练模型合并方法。[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]

arXiv cs.LG TIER_1 English(EN) · Akira Ito, Daiki Chijiwa, Atsutoshi Kumagai · 2026-11-11 05:00

基于置换的预训练模型通过互易正交性进行合并

arXiv:2611.13016v1 Announce Type: new Abstract: Ito et al. (2026) showed that sufficiently wide, independently trained neural networks can exhibit linear mode connectivity (LMC) with softmax temperature calibration, even without permutation. LMC means that a low-loss linear path …

本文如何被排名

报道来源 [1]

基于置换的预训练模型通过互易正交性进行合并

相关实体

相关话题