Graph Representation Learning Beyond Node and Homophily

3 Mar 2022  ·  You Li, Bei Lin, Binli Luo, Ning Gui ·

Unsupervised graph representation learning aims to distill various graph information into a downstream task-agnostic dense vector embedding. However, existing graph representation learning approaches are designed mainly under the node homophily assumption: connected nodes tend to have similar labels and optimize performance on node-centric downstream tasks. Their design is apparently against the task-agnostic principle and generally suffers poor performance in tasks, e.g., edge classification, that demands feature signals beyond the node-view and homophily assumption. To condense different feature signals into the embeddings, this paper proposes PairE, a novel unsupervised graph embedding method using two paired nodes as the basic unit of embedding to retain the high-frequency signals between nodes to support node-related and edge-related tasks. Accordingly, a multi-self-supervised autoencoder is designed to fulfill two pretext tasks: one retains the high-frequency signal better, and another enhances the representation of commonality. Our extensive experiments on a diversity of benchmark datasets clearly show that PairE outperforms the unsupervised state-of-the-art baselines, with up to 101.1\% relative improvement on the edge classification tasks that rely on both the high and low-frequency signals in the pair and up to 82.5\% relative performance gain on the node classification tasks.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification Citeseer PairE Accuracy 75.53 # 22
30% trainning, unsupervised with linear classfier Cora PairE Micro-F1 86.51 # 1
Node Classification Cora: fixed 20 node per class PairE Micro F1 75.12 # 1
Node Classification DBLP PairE Micro F1 80.58 # 2
Node Classification Deezer Romania PairE Micro-F1 0.68 # 1
Node Classification PPI PairE Micro F1 94.83 # 1
Node Classification Pubmed PairE F1 88.57 # 1