# Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation

arXiv: https://arxiv.org/abs/2607.09232 · HTML: https://mlsanity.com/paper/2607.09232/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https://mlsanity.com/paper/2205.14415/) (2022)
- [GOOD: A Graph Out-of-Distribution Benchmark](https://mlsanity.com/paper/2206.08452/) (2022)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [AdaRNN: Adaptive Learning and Forecasting of Time Series](https://mlsanity.com/paper/2108.04443/) (2021)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [Out-Of-Distribution Generalization on Graphs: A Survey](https://mlsanity.com/paper/2202.07987/) (2022)
- [A Re-evaluation of Knowledge Graph Completion Methods](https://mlsanity.com/paper/1911.03903/) (2019)
- [TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2109.04101/) (2021)
- [TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs](https://mlsanity.com/paper/2112.08025/) (2021)
- [TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs](https://mlsanity.com/paper/2406.09639/) (2024)
- [Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2203.07782/) (2022)
- [History repeats Itself: A Baseline for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2404.16726/) (2024)
- [CognTKE: A Cognitive Temporal Knowledge Extrapolation Framework](https://mlsanity.com/paper/2412.16557/) (2024)
- [History Repeats: Overcoming Catastrophic Forgetting For Event-Centric Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2305.18675/) (2023)
- [What Do Temporal Graph Learning Models Learn?](https://mlsanity.com/paper/2510.09416/) (2025)
- [REFOL: Resource-Efficient Federated Online Learning for Traffic Flow Forecasting](https://mlsanity.com/paper/2411.14046/) (2024)
- [Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2505.14020/) (2025)
- [A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2506.04083/) (2025)
- [T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs](https://mlsanity.com/paper/2507.10183/) (2025)
- [Deep Graph Learning will stall without Network Science](https://mlsanity.com/paper/2502.01177/) (2025)

## Abstract (arXiv)

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.