Heterogeneous Hypergraph Embedding for Graph Classification
Authors:
Open Access
- 8 March 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 725-733
Abstract
Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning. In the real world, a more natural and common situation is the coexistence of pairwise relationships and complex non-pairwise relationships, which is, however, rarely studied. In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise relations. Our framework first projects the heterogeneous hypergraph into a series of snapshots and then we take the Wavelet basis to perform localized hypergraph convolution. Since the Wavelet basis is usually much sparser than the Fourier basis, we develop an efficient polynomial approximation to the basis to replace the time-consuming Laplacian decomposition. Extensive evaluations have been conducted and the experimental results show the superiority of our method. In addition to the standard tasks of network embedding evaluation such as node classification, we also apply our method to the task of spammers detection and the superior performance of our framework shows that relationships beyond pairwise are also advantageous in the spammer detection. To make our experiment repeatable, source codes and related datasets are available at https://xiangguosun.mystrikingly.comKeywords
All Related Versions
Funding Information
- National Key R&D Program of China (2017YFB1003000)
- Australian Research Council (DP170103954, DP190101985)
This publication has 23 references indexed in Scilit:
- A novel social network hybrid recommender system based on hypergraph topologic structureWorld Wide Web, 2017
- Spatial-Aware Hierarchical Collaborative Deep Learning for POI RecommendationIEEE Transactions on Knowledge and Data Engineering, 2017
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs2017
- node2vec2016
- PTE2015
- LINE2015
- DeepWalk2014
- Visual-Textual Joint Relevance Learning for Tag-Based Social Image SearchIEEE Transactions on Image Processing, 2012
- Effective Sparse Matrix Representation For The GPU ArchitecturesInternational Journal of Computer Science, Engineering and Applications, 2012
- Fast unfolding of communities in large networksJournal of Statistical Mechanics: Theory and Experiment, 2008