DAPath: Distance-Aware Knowledge Graph Reasoning Based on DeepReinforcement Learning

HARI MOHAN PANDEY, Prayag Tiwari, Hongyin Zhu

Research output: Contribution to journalArticle (journal)peer-review

40 Citations (Scopus)
540 Downloads (Pure)


Knowledge graph reasoning aims to find reasoning paths for relations over incomplete knowledge graphs (KG). Prior works may not take into account that the rewards for each position (vertex in the graph) may be different. We propose the distance-aware reward in the reinforcement learning framework to assign different rewards for different positions. We observe that KG embeddings are learned from independent triples and therefore cannot fully cover the information described in the local neighborhood. To this effect, we integrate a graph self-attention (GSA) mechanism to capture more comprehensive entity information from the neighboring entities and relations. To let the model remember the path, we incorporate the GSA mechanism with GRU to consider the memory of relations in the path. Our approach can train the agent in one-pass, thus eliminating the pre-training or fine-tuning process, which significantly reduces the problem complexity. Experimental results demonstrate the effectiveness of our method. We found that our model can mine more balanced paths for each relation.
Original languageEnglish
Article numberNEUNET-D-20-00253R2
Number of pages12
JournalNeural Networks
Early online date5 Dec 2020
Publication statusE-pub ahead of print - 5 Dec 2020


  • Knowledge Graph Reasoning
  • Reinforcement Learning
  • Graph Self Attention
  • GRU


Dive into the research topics of 'DAPath: Distance-Aware Knowledge Graph Reasoning Based on DeepReinforcement Learning'. Together they form a unique fingerprint.

Cite this