An End-to-End Deep Learning Architecture for Graph Classification
Neural networks are typically designed to deal with data in tensor forms. In this paper, we propose a novel neural network architecture accepting graphs of arbitrary structure. Given a dataset containing graphs in the form of (G,y) where G is a graph and y is its class, we aim to develop neural networks that read the graphs directly and learn a classification function. There are two main challenges: 1) how to extract useful features characterizing the rich information encoded in a graph for classification purpose, and 2) how to sequentially read a graph in a meaningful and consistent order. To address the first challenge, we design a localized graph convolution model and show its connection with two graph kernels. To address the second challenge, we design a novel SortPooling layer which sorts graph vertices in a consistent order so that traditional neural networks can be trained on the graphs. Experiments on benchmark graph classification datasets demonstrate that the proposed architecture achieves highly competitive performance with state-of-the-art graph kernels and other graph neural network methods. Moreover, the architecture allows end-to-end gradient-based training with original graphs, without the need to first transform graphs into vectors.
PDF AbstractCode
Datasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Graph Classification | COLLAB | DGCNN (sum) | Accuracy | 69.45% | # 29 | |
Graph Classification | D&D | DGCNN (sum) | Accuracy | 78.72% | # 19 | |
Graph Classification | IMDb-B | DGCNN (sum) | Accuracy | 51.69% | # 40 | |
Graph Classification | IMDb-B | DGCNN | Accuracy | 70.03% | # 36 | |
Graph Classification | IMDb-M | DGCNN (sum) | Accuracy | 42.76% | # 34 | |
Graph Classification | IMDb-M | DGCNN | Accuracy | 47.83% | # 30 | |
Graph Classification | MUTAG | DGCNN | Accuracy | 85.83% | # 56 | |
Graph Classification | NCI1 | DGCNN (sum) | Accuracy | 69.00% | # 50 |