arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.13640cs.CLcs.AIcs.LG
收藏

基于自监督强化学习的知识图谱推理

Knowledge Graph Reasoning with Self-supervised Reinforcement Learning

School of Information and Electronics, Beijing Institute of Technology(北京理工大学信息与电子学院);University of Central Florida(中佛罗里达大学);Google(谷歌公司);Apple(苹果公司);Orby AI(Orby AI公司)

Ying Ma, Owen Burns, Mingqiu Wang, Gang Li, Nan Du, Laurent El Shafey, Liqiang Wang, Izhak Shafran, Hagen Soltau

AI总结:

针对不完整知识图谱推理中强化学习的大动作空间与分布不匹配问题,提出自监督预训练框架,提升策略网络性能,在四个基准数据集上指标超现有方法,可作为插件适配多种RL架构。

摘要:

强化学习(RL)是在不完整知识图谱(KGs)中寻找推理路径的有效方法。为应对大动作空间的挑战,提出一种自监督预训练方法,在RL训练阶段前预热策略网络。为缓解一般自监督RL(SSRL)中的分布不匹配问题,在监督学习(SL)阶段,智能体基于策略网络选择动作并从生成的标签中学习;这种标签自生成是“自监督”名称的由来。该训练框架提升了SL目标的信息密度,防止智能体陷入早期奖励路径。我们的自监督RL(SSRL)方法通过将RL与SL预训练的广泛覆盖相结合,提升了RL性能,因为SL目标的广度使其无法单独训练智能体。实验表明,在四个大型KG基准数据集上,我们的SSRL模型在所有Hits@k和平均倒数排名(MRR)指标上达到或超过当前最先进结果。该SSRL方法可作为任何KG推理(KGR)任务RL架构的插件。我们采用MINERVA和MultiHopKG两种RL架构作为基线模型,实验证明SSRL模型在所有四个KG推理任务上均持续优于这两种基线。完整代码可在https://github.com/owenonline/Knowledge-Graph-Reasoning-with-Self-supervised-Reinforcement-Learning获取。

英文摘要:

Reinforcement learning (RL) is an effective method of finding reasoning pathways in incomplete knowledge graphs (KGs). To overcome the challenges of a large action space, a self-supervised pre-training method is proposed to warm up the policy network before the RL training stage. To alleviate the distributional mismatch issue in general self-supervised RL (SSRL), in our supervised learning (SL) stage, the agent selects actions based on the policy network and learns from generated labels; this self-generation of labels is the intuition behind the name self-supervised. With this training framework, the information density of our SL objective is increased and the agent is prevented from getting stuck with the early rewarded paths. Our self-supervised RL (SSRL) method improves the performance of RL by pairing it with the wide coverage achieved by SL during pretraining, since the breadth of the SL objective makes it infeasible to train an agent with that alone. We show that our SSRL model meets or exceeds current state-of-the-art results on all Hits@k and mean reciprocal rank (MRR) metrics on four large benchmark KG datasets. This SSRL method can be used as a plug-in for any RL architecture for a KGR task. We adopt two RL architectures, i.e., MINERVA and MultiHopKG as our baseline RL models and experimentally show that our SSRL model consistently outperforms both baselines on all of these four KG reasoning tasks. Full code for the paper available at https://github.com/owenonline/Knowledge-Graph-Reasoning-with-Self-supervised-Reinforcement-Learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑