{"ID":2899134,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.01597","arxiv_id":"2507.01597","title":"T3DM: Test-Time Training-Guided Distribution Shift Modelling for Temporal Knowledge Graph Reasoning","abstract":"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.","short_abstract":"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 mo...","url_abs":"https://arxiv.org/abs/2507.01597","url_pdf":"https://arxiv.org/pdf/2507.01597v1","authors":"[\"Yuehang Si\",\"Zefan Zeng\",\"Jincai Huang\",\"Qing Cheng\"]","published":"2025-07-02T11:02:37Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\"]","methods":"[]","has_code":false}