BridgeMem：用于时序知识图谱预测的因果二元转移残差

中文摘要 AI 辅助

时序知识图谱预测旨在从观测事件的时间结构中推断未来的关系事实。现有的预测器主要通过实体状态、关系状态、路径或精确重复来概括历史。这些视角往往忽略了特定于二元组的转移证据，即查询主体与候选对象之间先前关系改变目标关系几率的方式。我们引入了BridgeMem，它将这一量估计为添加到冻结的全词汇预测器对数分数上的残差。对于每个候选对象，BridgeMem检索严格先于t的该二元组事件，编码它们的关系、方向和时滞，并将其转换为似然比校正。一个支持自适应的经验贝叶斯读取器在精确转移计数充足时信任它们，在稀疏时则退回到学习到的注意力估计器。骨干模型自身的不确定性门控该校正，因此对于有信心的查询和没有二元历史记录的候选对象，结果保持不变。在五个基准上，BridgeMem在2021年至2026年九种基线中最强的所有20个过滤MRR和Hits@{1,3,10}比较中均有所改进，MRR增益分别为0.0213、0.0164、0.0216、0.0112和0.0028，优于先前最佳结果。这些结果显示了显式二元转移建模的价值。

英文摘要

Temporal knowledge graph forecasting aims to infer future relational facts from the temporal structure of observed events. Existing forecasters mainly summarize history through entity states, relation states, paths, or exact recurrence. These views often miss pair-specific transition evidence, that is, the way prior relations between the query actor and a candidate change the odds of the target relation. We introduce BridgeMem, which estimates this quantity as a residual added to the log scores of a frozen full-vocabulary forecaster. For each candidate, BridgeMem retrieves the pair's events that strictly precede t, encodes their relations, directions, and lags, and converts them into a likelihood-ratio correction. A support-adaptive empirical-Bayes reader trusts exact transition counts where they are abundant and backs off to a learned attention estimator where they are sparse. The backbone's own uncertainty gates the correction, so confident queries and candidates without dyadic history are left unchanged. On five benchmarks, BridgeMem improves on the strongest of nine baselines from 2021--2026 in all 20 filtered MRR and Hits@{1,3,10} comparisons, with MRR gains of 0.0213, 0.0164, 0.0216, 0.0112, and 0.0028 over the best prior result. These results show the value of explicit dyadic transition modeling.

发表机构

• Shanghai Jiao Tong University（上海交通大学）
• University of Chicago（芝加哥大学）
• Jinan University（暨南大学）

机构由 AI 辅助整理，请以论文原文为准。