研究人员开发了RAPTOR，一种新颖的预训练方法，旨在提高时序知识图谱（TKG）推理的效率。这种自监督方法将可达性感知的归纳偏置注入到智能体中，使其能够更好地估计动作导向目标实体的潜力。通过减少对无望路径的探索，RAPTOR为强化学习（RL）微调提供了强大的初始化，从而在ICEWS14、ICEWS05-15和ICEWS18等数据集上显著提高了训练效率和性能。 AI
影响 提高了时序知识图谱推理的效率，可能改进对未来事件的预测。
排序理由 该集群包含一篇详细介绍时序知识图谱推理新方法的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2607.14886v1 Announce Type: new Abstract: 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)-…
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 …