DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning. (March 2021)

• Record Type: Journal Article
• Authors: Tiwari, Prayag; Zhu, Hongyin; Pandey, Hari Mohan
• Is Part Of: Neural networks. Volume 135(2021)
• Page Start: 1
• Page End: 12
• Publication Date: 2021-03
• Subjects: Knowledge graph reasoning -- Reinforcement learning -- Graph self-attention -- GRU; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2020.11.012
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: 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.