时间对齐的演化概念图用于科学关系预测

中文摘要 AI 辅助

预测科学关系可以通过在潜在联系出现之前识别有前景的联系来指导发现。现有方法通常分别建模概念语义和图结构，或在粗粒度历史快照上总结语义，导致语义表示可能与快速演化的图证据不对齐。我们提出了一种时间对齐的演化概念图框架，联合建模语义和结构演化。其核心思想是将带日期的论文视为共享更新事件，通过每个预测时间从相同的出版历史重建语义和结构状态。对级融合结合这些状态来预测首次共现、关系形成和条件关系类型。在保持架构和训练固定的情况下，随图更新刷新上下文相比冻结上下文将平均关系AUPRC提高了16.6%。在由187,848篇论文、270,687个概念和745万条共现链接构建的图上，完整框架将平均关系AUROC从最强评估基线的0.9290提升至0.9722，平均人口加权AUPRC为0.005778。

英文摘要

Forecasting scientific relations can guide discovery by identifying promising connections before they emerge. Existing approaches often model concept semantics and graph structure separately or summarize semantics over coarse historical snapshots, leaving semantic representations potentially misaligned with rapidly evolving graph evidence. We propose a time-aligned evolving concept graph framework that jointly models semantic and structural evolution. Its core idea is to treat dated papers as shared update events, reconstructing semantic and structural states from the same publication history through each prediction time. Pair-level fusion combines these states to forecast first co-occurrence, relation formation, and conditional relation type. Holding architecture and training fixed, refreshing context alongside graph updates improves mean relation AUPRC by 16.6% over frozen context. On a graph built from 187,848 papers with 270,687 concepts and 7.45 million co-occurrence links, the complete framework improves mean relation AUROC from 0.9290 for the strongest evaluated baseline to 0.9722, with mean population-weighted AUPRC 0.005778.

发表机构

• Tsinghua University（清华大学）
• Guangdong Institute of Intelligence Science and Technology（广东智能科学与技术研究院）

机构由 AI 辅助整理，请以论文原文为准。