arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.04029cs.AIcs.LG
收藏

RNNLogic:在知识图谱上学习推理逻辑规则

RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs

Université de Montréal(蒙特利尔大学);Mila - Québec AI Institute(米拉 - 魁北克人工智能研究所);Canadian Institute for Advanced Research (CIFAR)(加拿大高等研究院);HEC Montréal(蒙特利尔高等商学院);Tsinghua University(清华大学)

Meng Qu, Junkun Chen, Louis-Pascal Xhonneux, Yoshua Bengio, Jian Tang

摘要:

本文研究了在知识图谱上学习推理逻辑规则的问题。逻辑规则在用于预测时提供可解释的解释,并且能够推广到其他任务,因此对于学习至关重要。现有方法或者遭受在大的搜索空间中搜索的问题(例如,神经逻辑编程)或由于稀疏回报而导致的无效优化(例如,基于强化学习的技术)。为了解决这些限制,本文提出了一种称为RNNLogic的概率模型。RNNLogic将逻辑规则作为一个潜在变量,同时训练规则生成器和推理预测器。我们开发了一个基于EM的优化算法。在每次迭代中,首先更新推理预测器,以探索一些生成的逻辑规则进行推理。然后在E步骤中,我们选择一组高质量的规则,从所有生成的规则与规则生成器和推理预测器通过后验推理;和在M步骤中,规则生成器更新与E步骤中选择的规则。在四个数据集上的实验证明了RNNLogic的有效性。

英文摘要:

This paper studies learning logic rules for reasoning on knowledge graphs. Logic rules provide interpretable explanations when used for prediction as well as being able to generalize to other tasks, and hence are critical to learn. Existing methods either suffer from the problem of searching in a large search space (e.g., neural logic programming) or ineffective optimization due to sparse rewards (e.g., techniques based on reinforcement learning). To address these limitations, this paper proposes a probabilistic model called RNNLogic. RNNLogic treats logic rules as a latent variable, and simultaneously trains a rule generator as well as a reasoning predictor with logic rules. We develop an EM-based algorithm for optimization. In each iteration, the reasoning predictor is first updated to explore some generated logic rules for reasoning. Then in the E-step, we select a set of high-quality rules from all generated rules with both the rule generator and reasoning predictor via posterior inference; and in the M-step, the rule generator is updated with the rules selected in the E-step. Experiments on four datasets prove the effectiveness of RNNLogic.

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。

↑