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

arXiv: https://arxiv.org/abs/2507.01597 · HTML: https://mlsanity.com/paper/2507.01597/

## 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 (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs](https://mlsanity.com/paper/1705.05742/) (2017)
- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [Diachronic Embedding for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1907.03143/) (2019)
- [Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks](https://mlsanity.com/paper/2012.08492/) (2020)
- [TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2109.04101/) (2021)
- [KBGAN: Adversarial Learning for Knowledge Graph Embeddings](https://mlsanity.com/paper/1711.04071/) (2017)
- [Temporal Knowledge Graph Forecasting with Neural ODE](https://mlsanity.com/paper/2101.05151/) (2021)
- [Test-Time Training with Self-Supervision for Generalization under Distribution Shifts](https://mlsanity.com/paper/1909.13231/) (2019)
- [Temporal Knowledge Graph Reasoning with Historical Contrastive Learning](https://mlsanity.com/paper/2211.10904/) (2022)
- [Dual Test-time Training for Out-of-distribution Recommender System](https://mlsanity.com/paper/2407.15620/) (2024)
- [CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network](https://mlsanity.com/paper/2008.09388/) (2020)
- [ANDA: A Novel Data Augmentation Technique Applied to Salient Object Detection](https://mlsanity.com/paper/1910.01256/) (2019)
- [HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph](https://mlsanity.com/paper/2402.12074/) (2024)

## 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.