Journal
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING
Volume -, Issue -, Pages 406-415Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3292500.3330950
Keywords
Graph Neural Network; Degree-specific Convolution; Multi-task Learning; Graph Isomorphism Test
Funding
- United States Air Force [FA8750-17-C-0153]
- DARPA [FA8750-17-C-0153]
- National Science Foundation [IIS-1552654, IIS-1813464, CNS-1629888]
- U.S. Department of Homeland Security [17STQAC00001-02-00]
- IBM Faculty Award
Ask authors/readers for more resources
Graph data widely exist in many high-impact applications. Inspired by the success of deep learning in grid-structured data, graph neural network models have been proposed to learn powerful node-level or graph-level representation. However, most of the existing graph neural networks suffer from the following limitations: (1) there is limited analysis regarding the graph convolution properties, such as seed-oriented, degree-aware and order-free; (2) the node's degree specific graph structure is not explicitly expressed in graph convolution for distinguishing structure-aware node neighborhoods; (3) the theoretical explanation regarding the graph-level pooling schemes is unclear. To address these problems, we propose a generic degree-specific graph neural network named DEMO-Net motivated by Weisfeiler-Lehman graph isomorphism test that recursively identifies 1-hop neighborhood structures. In order to explicitly capture the graph topology integrated with node attributes, we argue that graph convolution should have three properties: seed-oriented, degree-aware, order-free. To this end, we propose multi-task graph convolution where each task represents node representation learning for nodes with a specific degree value, thus leading to preserving the degree specific graph structure. In particular, we design two multi-task learning methods: degree-specific weight and hashing functions for graph convolution. In addition, we propose a novel graph-level pooling/readout scheme for learning graph representation provably lying in a degree-specific Hilbert kernel space. The experimental results on several node and graph classification benchmark data sets demonstrate the effectiveness and efficiency of our proposed DEMO-Net over state-of-the-art graph neural network models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available