RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
This addresses the challenge of interpretable and generalizable reasoning in knowledge graphs, which is incremental as it builds on prior methods like neural logic programming and reinforcement learning.
The paper tackles the problem of learning logic rules for reasoning on knowledge graphs by proposing RNNLogic, a probabilistic model that treats rules as latent variables and uses an EM-based algorithm to train a rule generator and reasoning predictor simultaneously, achieving effectiveness validated on four datasets.
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.