针对时序知识图谱推理中的分布偏移问题，提出测试时训练引导的建模方法。
T3DM: Test-Time Training-Guided Distribution Shift Modelling for Temporal Knowledge Graph Reasoning
- 利用测试时训练动态调整模型以应对训练与测试数据的分布差异
- 在多个基准上显著提升推理性能，优于现有最优方法
- 适合需要高鲁棒性时序推理的应用场景
时序知识图谱（TKG）是描述事实随时间动态演变的有效方式。当前大多数时序知识图谱推理（TKGR）研究聚焦于全局事实重复性和局部历史模式建模，但面临两大挑战：训练与测试样本间事件分布偏移建模不足，以及依赖随机实体替换生成负样本，导致采样质量低下。为此，我们提出一种新的分布特征建模方法——测试时训练引导的分布偏移建模（T3DM），通过测试时训练调整模型，确保推理全局一致性。此外，设计基于对抗训练的负样本生成策略，提升负三元组质量。大量实验表明，T3DM在多数情况下优于当前最优基线，表现更优且更鲁棒。
原文摘要 · Abstract (English)
Temporal Knowledge Graph (TKG) is an efficient method for describing the dynamic development of facts along a timeline. Most research on TKG reasoning (TKGR) focuses on modelling the repetition of global facts and designing patterns of local historical facts. However, they face two significant challenges: inadequate modeling of the event distribution shift between training and test samples, and reliance on random entity substitution for generating negative samples, which often results in low-quality sampling. To this end, we propose a novel distributional feature modeling approach for training TKGR models, Test-Time Training-guided Distribution shift Modelling (T3DM), to adjust the model based on distribution shift and ensure the global consistency of model reasoning. In addition, we design a negative-sampling strategy to generate higher-quality negative quadruples based on adversarial training. Extensive experiments show that T3DM provides better and more robust results than the state-of-the-art baselines in most cases.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。