LAUSR

Reinforcement learning (RL)-based multi-hop reasoning has become an interpretable way for knowledge graph reasoning owing to its persuasive explanations for the predicted results, but the reasoning performance of these methods drops significantly over few-shot relations (only contain few triplets). To address this problem, recent studies introduce meta-learning into RL-based reasoning methods. However, the performance of these studies is still limited due to the following points: (1) the overall reasoning accuracy is impaired due to the low reasoning accuracies over some hard relations; (2) the reasoning process becomes laborious and ineffective owing to the existence of noisy data; (3) the generalizability is negatively affected due to the lack of knowledge-sharing. To tackle these challenges, we propose a novel model HMLS consisting of two modules HHML (Hierarchical Hardness-aware Meta-reinforcement Learning) and HHS (Hierarchical Hardness-aware Sampling). Specifically, HHML contains the following two components: (1) a hardness-aware RL conducts multi-hop reasoning by training hardness-aware batches and reducing noise; (2) a knowledge-sharing meta-learning adapts to few-shot relations by exploiting common features in the hierarchical relation structure. The other module HHS generates hardness-aware batches from relation and relation-cluster levels. The experimental results demonstrate that this work notably outperforms the state-of-the-art approaches in few-shot scenarios.