English(EN) LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models

LoGIC 方法优化表格基础模型的图上下文学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了 LoGIC，一种使用表格基础模型优化节点级图上下文学习（ICL）中上下文构建的新颖方法。LoGIC 通过智能选择用于提示的标记和未标记节点，解决了使用完整训练表相关的二次扩展和内存瓶颈问题。该系统通过结构、基于特征和覆盖通道检索标记节点，并为适配器消息传递引入了未标记光环。在 GraphLand 数据集上的实验表明，LoGIC 在保持与全上下文方法相当的性能的同时，显著降低了内存需求，从而无需重新训练即可在百万节点图上实现 ICL。 AI

影响优化了图 ICL 的上下文构建，有可能使用现有的表格基础模型实现更大规模的图分析。

排序理由这是一篇详细介绍图上下文学习新方法的学术论文。[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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍图上下文学习新方法的学术论文。[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, infra; 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) · Mingqi Yang, Zidong Guo, Jihui Yang, Wenming Zuo · 2026-09-10 04:00

LoGIC：用于表格基础模型的节点级图上下文学习的预算上下文构建

arXiv:2609.05955v1 Announce Type: new Abstract: Tabular foundation models have become powerful graph learners. Systems such as G2T-FM and GraphPFN encode each node as a feature row and make predictions through in-context learning (ICL), with labeled rows serving as the prompt. Cu…

本文如何被排名

报道来源 [1]

LoGIC：用于表格基础模型的节点级图上下文学习的预算上下文构建

相关实体

相关话题