IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification

22 Jul 2019  ยท  Lin Meng, Jiawei Zhang ยท

Deep learning models have achieved huge success in numerous fields, such as computer vision and natural language processing. However, unlike such fields, it is hard to apply traditional deep learning models on the graph data due to the 'node-orderless' property. Normally, adjacency matrices will cast an artificial and random node-order on the graphs, which renders the performance of deep models on graph classification tasks extremely erratic, and the representations learned by such models lack clear interpretability. To eliminate the unnecessary node-order constraint, we propose a novel model named Isomorphic Neural Network (IsoNN), which learns the graph representation by extracting its isomorphic features via the graph matching between input graph and templates. IsoNN has two main components: graph isomorphic feature extraction component and classification component. The graph isomorphic feature extraction component utilizes a set of subgraph templates as the kernel variables to learn the possible subgraph patterns existing in the input graph and then computes the isomorphic features. A set of permutation matrices is used in the component to break the node-order brought by the matrix representation. Three fully-connected layers are used as the classification component in IsoNN. Extensive experiments are conducted on benchmark datasets, the experimental results can demonstrate the effectiveness of ISONN, especially compared with both classic and state-of-the-art graph classification methods.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Classification BP-fMRI-97 IsoNN-fast Accuracy 62.3% # 3
F1 63.2% # 4
Graph Classification BP-fMRI-97 IsoNN Accuracy 64.9% # 1
F1 69.7% # 1
Graph Classification HIV-DTI-77 IsoNN Accuracy 67.5% # 1
F1 68.3% # 1
Graph Classification HIV-DTI-77 IsoNN-fast Accuracy 60.1% # 3
F1 61.9% # 3
Graph Classification HIV-fMRI-77 IsoNN Accuracy 73.4 # 1
F1 72.2 # 1
Graph Classification HIV-fMRI-77 IsoNN Accuracy 73.4% # 1
F1 72.2% # 1
Graph Classification HIV-fMRI-77 IsoNN-Fast Accuracy 70.5% # 2
F1 69.9% # 2
Graph Classification MUTAG Function Space Pooling Accuracy 83.3% # 63
Graph Classification PTC IsoNN Accuracy 59.9% # 35

Methods


No methods listed for this paper. Add relevant methods here