mlsanityData to 14 Oct 2026

T3DM: Test-Time Training-Guided Distribution Shift Modelling for Temporal Knowledge Graph Reasoning

arXiv 2507.01597 ↗First posted 2 Jul 2025cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 37 references that are in the map. First posted on arXiv 2 Jul 2025.

Builds on

19 of 37 references.

References · 19

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  4. 2016Complex Embeddings for Simple Link Predictioncited by 902
  5. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  6. 2017Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphscited by 149
  7. 2018Learning Sequence Encoders for Temporal Knowledge Graph Completioncited by 145
  8. 2021Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learningcited by 106
  9. 2019Diachronic Embedding for Temporal Knowledge Graph Completioncited by 104
  10. 2020Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networkscited by 84
  11. 2021TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecastingcited by 67
  12. 2017KBGAN: Adversarial Learning for Knowledge Graph Embeddingscited by 62
7 more
  1. 2021Temporal Knowledge Graph Forecasting with Neural ODEcited by 61
  2. 2019Test-Time Training with Self-Supervision for Generalization under Distribution Shiftscited by 59
  3. 2022Temporal Knowledge Graph Reasoning with Historical Contrastive Learningcited by 42
  4. 2024Dual Test-time Training for Out-of-distribution Recommender Systemcited by 16
  5. 2020CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Networkcited by 8
  6. 2019ANDA: A Novel Data Augmentation Technique Applied to Salient Object Detectioncited by 4
  7. 2024HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graphcited by 4

Built on by

Not cited yet.