发表机构
Data and Web Science Group, University of Mannheim; SAP Signavio（曼海姆大学数据与网络科学组; 思爱普公司 Signavio）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究在分布转移下时态知识图谱预测问题，借助合成TKG生成器编码时间和结构属性，评估七种预测架构，发现其鲁棒性依赖信号，循环和周期性规律在平稳时可恢复，结构突变暴露模型适应性局限，增进对TKG模型的理解。
AI 中文摘要
时态知识图谱（TKGs）代表不断演变的关系系统，其基础数据生成过程常随时间变化。然而，TKG预测模型通常仅在经验基准数据集上评估，对模型面对此类分布转移的鲁棒性洞察有限。我们使用合成TKG生成器研究在可控转移环境下的TKG预测，该生成器将三种时间和结构属性——循环性、同质性和周期性——编码为数据生成机制。这使我们能评估七种预测架构在平稳和转移状态下的表现。实验表明，TKG预测中的鲁棒性高度依赖信号。基于循环和周期性规律在平稳条件下大多可恢复，当循环性主导数据时，简单基于记忆的基线可能具有竞争力。然而，结构突变揭示了模型适应性的局限性，潜在实体社区结构的变化在我们的研究中构成了最大挑战。总体而言，我们的发现增进了对当前TKG模型面对时间分布转移时的能力和局限性的理解。
英文摘要
Temporal knowledge graphs (TKGs) represent evolving relational systems, whose underlying data-generating processes often change over time. Yet, TKG forecasting models are commonly evaluated only on empirical benchmark datasets that provide limited insight into the models' robustness to such distribution shifts. Recognising this issue, we study TKG forecasting under controlled shift environments using a synthetic TKG generator that encodes three temporal and structural properties -- recurrence, homophily, and periodicity -- as data-generating mechanisms. This allows us to evaluate seven forecasting architectures under stationary and shifting regimes. Our experiments suggest that robustness in TKG forecasting is highly signal-dependent. Recurrence-based and periodic regularities are largely recoverable under stationary conditions, and simple memory-based baselines can be competitive when recurrence dominates the data. However, structural breaks reveal limitations in model adaptivity, with shifts in latent entity-community structure posing the strongest challenge in our study. Overall, our findings improve the understanding of the capabilities and limitations of current TKG models confronted with temporal distribution shifts.
CommentsAccepted at ECML PKDD 2026 Workshops
