A comparative study of similarity-based and GNN-based link prediction approaches
arXiv:2008.08879
Abstract
The task of inferring the missing links in a graph based on its current structure is referred to as link prediction. Link prediction methods that are based on pairwise node similarity are well-established approaches in the literature. They show good prediction performance in many real-world graphs though they are heuristics and lack of universal applicability. On the other hand, the success of neural networks for classification tasks in various domains leads researchers to study them in graphs. When a neural network can operate directly on the graph, then it is termed as the graph neural network (GNN). GNN is able to learn hidden features from graphs which can be used for link prediction task in graphs. Link predictions based on GNNs have gained much attention of researchers due to their convincing high performance in many real-world graphs. This appraisal paper studies some similarity and GNN-based link prediction approaches in the domain of homogeneous graphs that consists of a single type of (attributed) nodes and single type of pairwise links. We evaluate the studied approaches against several benchmark graphs with different properties from various domains.
arXiv commentGEM Workshop, ECML-PKDD 2020
References in corpus (13)
- Emergence of scaling in random networks
- Finding community structure in networks using the eigenvectors of matrices
- Inductive Representation Learning on Large Graphs
- Hierarchical organization of modularity in metabolic networks
- Predicting Missing Links via Local Information
- A Review of Relational Machine Learning for Knowledge Graphs
- Modeling polypharmacy side effects with graph convolutional networks
- Vertex similarity in networks
- Adaptive Sampling Towards Fast Graph Representation Learning
- Reconstructing propagation networks with natural diversity and identifying hidden sources
- Link Prediction with Node Clustering Coefficient
- Link prediction based on path entropy
- Improving local clustering based top-L link prediction methods via asymmetrical link clustering information