# Reachability-Aware Pretraining for Efficient Target-Oriented Path Exploration in Temporal Knowledge Graph Reasoning

arXiv: https://arxiv.org/abs/2607.14886 · HTML: https://mlsanity.com/paper/2607.14886/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [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)
- [Diachronic Embedding for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1907.03143/) (2019)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [Question Answering Over Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.01515/) (2021)
- [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)
- [HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph](https://mlsanity.com/paper/2402.12074/) (2024)
- [Knowledge Graph Reasoning with Self-supervised Reinforcement Learning](https://mlsanity.com/paper/2405.13640/) (2024)

## Abstract (arXiv)

Temporal Knowledge Graph (TKG) reasoning under the extrapolation setting focuses on forecasting future time-stamped events (facts) from historical data in a temporal knowledge graph. Existing approaches, reinforcement learning (RL)-based multi-hop reasoning methods are prominent for TKG reasoning because they produce human-interpretable predictions via explicit multi-hop path tracing. However, during RL training, rewards are typically sparse, and exploration is highly inefficient due to the vast, time-evolving action space. These issues hinder efficient training and often limit overall performance. To address these challenges, we propose RAPTOR (Reachability-Aware Pretraining for Efficient Target-Oriented Path Exploration), a self-supervised pretraining method that injects a reachability-aware inductive bias to the agent. By learning to estimate the reachability of candidate actions to the target entity, RAPTOR reduces exploration over unpromising paths and provides a strong initialization for downstream RL fine-tuning. Experimental results on the ICEWS14, ICEWS05-15, and ICEWS18 datasets demonstrate that RAPTOR pretraining markedly improves the training efficiency and consistently outperforms conventional baselines, establishing it as an effective approach for enhancing RL-based multi-hop reasoning methods for TKG reasoning.