LGFeb 24, 2021

Benchmarking Graph Neural Networks on Link Prediction

arXiv:2102.12557v113 citations
Originality Synthesis-oriented
AI Analysis

This provides a fair and systematic comparison for researchers working on link prediction with GNNs, but it is incremental as it replicates and analyzes existing methods without introducing new techniques.

The paper benchmarks existing graph neural network models like GCN, GraphSAGE, GAT, and VGAE on link prediction tasks across datasets, finding that these architectures perform similarly on various benchmarks.

In this paper, we benchmark several existing graph neural network (GNN) models on different datasets for link predictions. In particular, the graph convolutional network (GCN), GraphSAGE, graph attention network (GAT) as well as variational graph auto-encoder (VGAE) are implemented dedicated to link prediction tasks, in-depth analysis are performed, and results from several different papers are replicated, also a more fair and systematic comparison are provided. Our experiments show these GNN architectures perform similarly on various benchmarks for link prediction tasks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes