Composition-based Multi-Relational Graph Convolutional Networks
arXiv:1911.03082
Abstract
Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it. Most of the existing approaches to handle such graphs suffer from over-parameterization and are restricted to learning representations of nodes only. In this paper, we propose CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph. CompGCN leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations. It also generalizes several of the existing multi-relational GCN methods. We evaluate our proposed method on multiple tasks such as node classification, link prediction, and graph classification, and achieve demonstrably superior results. We make the source code of CompGCN available to foster reproducible research.
In Proceedings of ICLR 2020
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Neural Message Passing for Quantum Chemistry
- A Review of Relational Machine Learning for Knowledge Graphs
- Fast Graph Representation Learning with PyTorch Geometric
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- Hypernetwork Knowledge Graph Embeddings
- Dual-Primal Graph Convolutional Networks
Cited by in corpus (5)
- HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
- Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
- Enhancing Heterogeneous Knowledge Graph Completion with a Novel GAT-based Approach
- Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
- TANGNN: a Concise, Scalable and Effective Graph Neural Networks with Top-m Attention Mechanism for Graph Representation Learning