Graph-Graph Similarity Network

• Published in: IEEE transaction on neural networks and learning systems Vol. 35; no. 7; pp. 9136 - 9146
• Main Authors: Yue, Han, Hong, Pengyu, Liu, Hongfu
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aggregates; Algorithms; Benchmarks; Cognitive tasks; Crystals; Feature extraction; Graph neural networks; Graph representations; Graph theory; Graphical representations; Graphs; Labels; Learning; Machine learning; Measurement; metric learning; Neural networks; Nodes; Prediction algorithms; Similarity; supervised learning; Task analysis
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2022.3218936

Graph learning aims to predict the label for an entire graph. Recently, graph neural network (GNN)-based approaches become an essential strand to learning low-dimensional continuous embeddings of entire graphs for graph label prediction. While GNNs explicitly aggregate the neighborhood information and implicitly capture the topological structure for graph representation, they ignore the relationships among graphs. In this article, we propose a graph-graph (G2G) similarity network to tackle the graph learning problem by constructing a SuperGraph through learning the relationships among graphs. Each node in the SuperGraph represents an input graph, and the weights of edges denote the similarity between graphs. By this means, the graph learning task is then transformed into a classical node label propagation problem. Specifically, we use an adversarial autoencoder to align embeddings of all the graphs to a prior data distribution. After the alignment, we design the G2G similarity network to learn the similarity between graphs, which functions as the adjacency matrix of the SuperGraph. By running node label propagation algorithms on the SuperGraph, we can predict the labels of graphs. Experiments on five widely used classification benchmarks and four public regression benchmarks under a fair setting demonstrate the effectiveness of our method.