# TKGB: A Comprehensive Benchmark for Temporal Knowledge Graph Forecasting

arXiv: https://arxiv.org/abs/2602.08353 · HTML: https://mlsanity.com/paper/2602.08353/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [Tensor Decompositions for temporal knowledge base completion](https://mlsanity.com/paper/2004.04926/) (2020)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [Temporal Knowledge Graph Forecasting with Neural ODE](https://mlsanity.com/paper/2101.05151/) (2021)
- [Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning](https://mlsanity.com/paper/2305.10613/) (2023)
- [Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2402.14382/) (2024)
- [HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces](https://mlsanity.com/paper/2312.13680/) (2023)
- [Co-Neighbor Encoding Schema: A Light-cost Structure Encoding Method for Dynamic Link Prediction](https://mlsanity.com/paper/2407.20871/) (2024)
- [A Unified Temporal Knowledge Graph Reasoning Model Towards Interpolation and Extrapolation](https://mlsanity.com/paper/2405.18106/) (2024)
- [Knowledge-augmented Graph Machine Learning for Drug Discovery: A Survey](https://mlsanity.com/paper/2302.08261/) (2023)
- [GTRL: An Entity Group-Aware Temporal Knowledge Graph Representation Learning Method](https://mlsanity.com/paper/2302.11091/) (2023)

## Abstract (arXiv)

Temporal knowledge graph (TKG) forecasting has advanced remarkably in recent years. Yet we found existing benchmarks inadvertently introduce a shortcut: For a subset of test queries, models can achieve optimal evaluation metrics without using any time information. We trace this to two pieces of evidence: inherent dataset biases and an overly simplistic task formulation that allows models to exploit biases, revealing fundamental flaws in current evaluation protocols for differentiating true forecasting ability. Moreover, existing datasets rely on fixed history that poorly reflects real-world dynamics, lack semantic context, and fail to explicitly mitigate shortcut, preventing thorough assessment of forecasting abilities. To address these, we propose TKGB, a comprehensive benchmark for evaluating the capability of TKG forecasting models. By integrating four complementary tasks with an automatic pipeline for constructing up-to-date and context-enriched TKG datasets with controllable shortcuts, TKGB reveals capability differences and failure modes hidden under conventional evaluation.