Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation

• URL: http://arxiv.org/abs/2607.09232v1
• Date: Fri, 10 Jul 2026 09:22:19 GMT
• Title: Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation
• Abstract summary: We study TKG forecasting under controlled shift environments using a synthetic TKG generator.<n>Our experiments suggest that robustness in TKG forecasting is highly signal-dependent.<n> structural breaks reveal limitations in model adaptivity, with shifts in latent entity-community structure posing the strongest challenge.
• Score: 11.079423042176904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Preserving Temporal Dynamics in Time Series Generation [0.2099922236065961]
  Time-series data augmentation plays a crucial role in regression-oriented forecasting tasks.<n>Existing approaches primarily focus on matching marginal data distributions.<n>We propose a model-agnostic Markov Chain Monte Carlo framework to mitigate distribution shift and preserve temporal dynamics.
  arXiv  Detail & Related papers  (2026-04-29T20:32:45Z)
• Graph2TS: Structure-Controlled Time Series Generation via Quantile-Graph VAEs [1.0499611180329804]
  We propose a structure-residual perspective on time-series generation, viewing temporal data as the combination of a structural backbone and residual dynamics.<n>By conditioning generation on structure rather than labels or metadata, the model preserves global temporal organization while enabling controlled variation.<n> Experiments on diverse datasets, including sunspot, electricity load, ECG, and EEG signals, demonstrate improved distributional fidelity, temporal alignment, and representativeness compared to diffusion- and GAN-based baselines.
  arXiv  Detail & Related papers  (2026-03-20T14:12:11Z)
• Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gains [17.650604674194984]
  We argue that the current practice of evaluating AI/ML time-series forecasting models obscures real progress by overlooking the performance of efficient classical methods.<n>We demonstrate that these "standard" datasets often exhibit dominant autocorrelation patterns and seasonal cycles that can be effectively captured by simpler linear or statistical models.
  arXiv  Detail & Related papers  (2026-03-16T16:34:26Z)
• A Representation-Consistent Gated Recurrent Framework for Robust Medical Time-Series Classification [0.0]
  We propose a representation-consistent gated recurrent framework (RC-GRF) that introduces a principled regularization strategy to enforce temporal consistency in hidden-state representations.<n>The proposed framework is model-agnostic and can be integrated into existing gated recurrent architectures without modifying their internal gating mechanisms.
  arXiv  Detail & Related papers  (2026-02-10T17:16:49Z)
• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• Topology-Aware Conformal Prediction for Stream Networks [68.02503121089633]
  We propose Spatio-Temporal Adaptive Conformal Inference (textttCISTA), a novel framework that integrates network topology and temporal dynamics into the conformal prediction framework.<n>Our results show that textttCISTA effectively balances prediction efficiency and coverage, outperforming existing conformal prediction methods for stream networks.
  arXiv  Detail & Related papers  (2025-03-06T21:21:15Z)
• Powerformer: A Transformer with Weighted Causal Attention for Time-series Forecasting [50.298817606660826]
  We introduce Powerformer, a novel Transformer variant that replaces noncausal attention weights with causal weights that are reweighted according to a smooth heavy-tailed decay.<n>Our empirical results demonstrate that Powerformer achieves state-of-the-art accuracy on public time-series benchmarks.<n>Our analyses show that the model's locality bias is amplified during training, demonstrating an interplay between time-series data and power-law-based attention.
  arXiv  Detail & Related papers  (2025-02-10T04:42:11Z)
• A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics [51.147876395589925]
  A non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time. A fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance.
  arXiv  Detail & Related papers  (2024-02-26T04:39:01Z)
• GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models [35.594662986581746]
  Large language models (LLMs) have ignited interest in the temporal knowledge graph (tKG) domain, where conventional embedding-based and rule-based methods dominate. We propose a novel retrieval-augmented generation framework named GenTKG combining a temporal logical rule-based retrieval strategy and few-shot parameter-efficient instruction tuning. Experiments have shown that GenTKG outperforms conventional methods of temporal relational forecasting with low computation resources.
  arXiv  Detail & Related papers  (2023-10-11T18:27:12Z)
• Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning [59.004025528223025]
  Key to predict future facts is to thoroughly understand the historical facts. A TKG is actually a sequence of KGs corresponding to different timestamps. We propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN)
  arXiv  Detail & Related papers  (2021-04-21T05:12:21Z)
• Stochastically forced ensemble dynamic mode decomposition for forecasting and analysis of near-periodic systems [65.44033635330604]
  We introduce a novel load forecasting method in which observed dynamics are modeled as a forced linear system. We show that its use of intrinsic linear dynamics offers a number of desirable properties in terms of interpretability and parsimony. Results are presented for a test case using load data from an electrical grid.
  arXiv  Detail & Related papers  (2020-10-08T20:25:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.