Heterogeneous Hypergraph Embedding for Graph Classification
Authors:
- Xiangguo SunXSXiangguo Sun
- Hongzhi YinHYHongzhi Yin
- Bo LiuBLBo Liu
- Hongxu ChenHCHongxu Chen
- Jiuxin CaoJCJiuxin Cao
- Yingxia ShaoYSYingxia Shao
- Nguyen Quoc Viet HungNHNguyen Quoc Viet Hung
Preprint
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.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Co-Detection of crowdturfing microblogs and spammers in online social networksWorld Wide Web, 2019
- Graph Convolutional Networks for Temporal Action Localization2019
- Social-Guided Representation Learning for Images via Deep Heterogeneous Hypergraph Embedding2018
- Dynamic Feature Selection Algorithm Based on Minimum Vertex Cover of Hypergraph2018
- A novel social network hybrid recommender system based on hypergraph topologic structureWorld Wide Web, 2017
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs2017
- Applications of Hypergraph Theory: A Brief Overview2013
- Learning on Weighted Hypergraphs to Integrate Protein Interactions and Gene Expressions for Cancer Outcome Prediction2008
- Learning a Hidden HypergraphLecture Notes in Computer Science, 2005
- Automating the Construction of Internet Portals with Machine LearningInformation Retrieval Journal, 2000