GAFM: A Knowledge Graph Completion Method Based on Graph Attention Faded Mechanism |
| |
| Institution: | 1. College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, China 450002;2. School of Cyber Science and Engineering, Wuhan University, Wuhan, China 430079;3. School of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China 450045;4. Henan Key Laboratory of Cyberspace Situation Awareness, Zhengzhou 450001;1. School of Information Management, Nanjing University, Nanjing 210023, China;2. School of Computer Science and Engineering, Southeast University, Nanjing 210096, China;3. School of Economics and Management, Nanjing University of Science and Technology, Nanjing 210094, China;1. School of Computing and Information, University of Pittsburgh, Pittsburgh, Pennsylvania, USA;2. School of Information Science, University of Kentucky, Lexington, Kentucky, USA;3. School of Nursing, The University of Texas at Austin, Austin, Texas, USA;4. School of Information, The University of Texas at Austin, Austin, Texas, USA;1. School of Information, Florida State University, Tallahassee, Florida USA;2. College of Medicine, Florida State University, Tallahassee, Florida USA;3. Department of Statistics, Florida State University, Tallahassee, Florida USA;4. Department of Computer Science, Florida State University, Tallahassee, Florida USA;5. Department of Psychology, Florida State University, Tallahassee, Florida USA;6. Department of Psychology, University of Central Florida, Orlando, Florida USA;7. Department of Psychology, The University of Alabama, Tuscaloosa, Alabama USA |
| |
| Abstract: | Although the Knowledge Graph (KG) has been successfully applied to various applications, there is still a large amount of incomplete knowledge in the KG. This study proposes a Knowledge Graph Completion (KGC) method based on the Graph Attention Faded Mechanism (GAFM) to solve the problem of incomplete knowledge in KG. GAFM introduces a graph attention network that incorporates the information in multi-hop neighborhood nodes to embed the target entities into low dimensional space. To generate a more expressive entity representation, GAFM gives different weights to the neighborhood nodes of the target entity by adjusting the attention value of neighborhood nodes according to the variation of the path length. The attention value is adjusted by the attention faded coefficient, which decreases with the increase of the distance between the neighborhood node and the target entity. Then, considering that the capsule network has the ability to fit features, GAFM introduces the capsule network as the decoder to extract feature information from triple representations. To verify the effectiveness of the proposed method, we conduct a series of comparative experiments on public datasets (WN18RR and FB15k-237). Experimental results show that the proposed method outperforms baseline methods. The Hits@10 metric is improved by 8% compared with the second-place KBGAT method. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
