A graph similarity for deep learning
Graph neural networks (GNNs) have been successful in learning representations from graphs. Many popular GNNs follow the pattern of aggregate-transform: they aggregate the neighbors' attributes and then transform the results of aggregation with a learnable function. Analyses of these GNNs explain which pairs of non-identical graphs have different representations. However, we still lack an understanding of how similar these representations will be. We adopt kernel distance and propose transform-sum-cat as an alternative to aggregate-transform to reflect the continuous similarity between the node neighborhoods in the neighborhood aggregation. The idea leads to a simple and efficient graph similarity, which we name Weisfeiler-Leman similarity (WLS). In contrast to existing graph kernels, WLS is easy to implement with common deep learning frameworks. In graph classification experiments, transform-sum-cat significantly outperforms other neighborhood aggregation methods from popular GNN models. We also develop a simple and fast GNN model based on transform-sum-cat, which obtains, in comparison with widely used GNN models, (1) a higher accuracy in node classification, (2) a lower absolute error in graph regression, and (3) greater stability in adversarial training of graph generation.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningGraph ClassificationGraph GenerationGraph RegressionGraph SimilarityNode ClassificationSimilar Papers 제목 키워드 기반
Convolutional Set Matching for Graph Similarity
We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs. As the core operation of graph similarity search, pairwise graph similarity co…
Graph Similarityset matchingCGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning
Graph similarity learning refers to calculating the similarity score between two graphs, which is required in many realistic applications, such as visual tracking, graph classification, and collaborative filtering. As mo…
Collaborative FilteringGraph ClassificationGraph MatchingGraph Similarity+2Learning-based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching
Graph similarity computation is one of the core operations in many graph-based applications, such as graph similarity search, graph database analysis, graph clustering, etc. Since computing the exact distance/similarity …
ClusteringCombinatorial OptimizationGraph ClassificationGraph Clustering+3More Interpretable Graph Similarity Computation via Maximum Common Subgraph Inference
Graph similarity measurement, which computes the distance/similarity between two graphs, arises in various graph-related tasks. Recent learning-based methods lack interpretability, as they directly transform interaction …
Graph ClassificationGraph SimilarityNeural Network Graph Similarity Computation Based on Graph Fusion
Graph similarity learning, crucial for tasks such as graph classification and similarity search, focuses on measuring the similarity between two graph-structured entities. The core challenge in this field is effectively …
Graph ClassificationGraph Similarity