arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.00571cs.AIcs.CLcs.LG
收藏

基于规则指导的协作Agent知识图谱推理

Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning

University of Southern California(南加州大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Deren Lei, Gangrong Jiang, Xiaotao Gu, Kexuan Sun, Yuning Mao, Xiang Ren

摘要:

基于Walk的模型在知识图谱(KG)推理中表现出了其优势,在提供可解释决策的同时实现了良好的性能。然而,KG在遍历期间提供的稀疏奖励信号通常不足以指导复杂的基于行走的强化学习(RL)模型。另一种方法是使用传统的符号方法(例如,规则归纳),取得了良好的性能,但由于符号表示的限制,很难推广。在本文中,我们提出了RuleGuider,它利用基于符号的方法生成的高质量规则,为基于行走的代理提供奖励监督。在基准数据集上的实验表明,RuleGuider在不损失可解释性的情况下提高了基于行走的模型的性能。

英文摘要:

Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions. However, the sparse reward signals offered by the KG during traversal are often insufficient to guide a sophisticated walk-based reinforcement learning (RL) model. An alternate approach is to use traditional symbolic methods (e.g., rule induction), which achieve good performance but can be hard to generalize due to the limitation of symbolic representation. In this paper, we propose RuleGuider, which leverages high-quality rules generated by symbolic-based methods to provide reward supervision for walk-based agents. Experiments on benchmark datasets show that RuleGuider improves the performance of walk-based models without losing interpretability.

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。

↑