Graph Dilated Network with Rejection Mechanism
Open Access
- 2 April 2020
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 10 (7), 2421
- https://doi.org/10.3390/app10072421
Abstract
Recently, graph neural networks (GNNs) have achieved great success in dealing with graph-based data. The basic idea of GNNs is iteratively aggregating the information from neighbors, which is a special form of Laplacian smoothing. However, most of GNNs fall into the over-smoothing problem, i.e., when the model goes deeper, the learned representations become indistinguishable. This reflects the inability of the current GNNs to explore the global graph structure. In this paper, we propose a novel graph neural network to address this problem. A rejection mechanism is designed to address the over-smoothing problem, and a dilated graph convolution kernel is presented to capture the high-level graph structure. A number of experimental results demonstrate that the proposed model outperforms the state-of-the-art GNNs, and can effectively overcome the over-smoothing problem.This publication has 13 references indexed in Scilit:
- NMLPA: Uncovering Overlapping Communities in Attributed Networks via a Multi-Label Propagation ApproachSensors, 2019
- DeepDirect: Learning Directions of Social Ties with Edge-Based Network EmbeddingIEEE Transactions on Knowledge and Data Engineering, 2018
- Graph embedding techniques, applications, and performance: A surveyKnowledge-Based Systems, 2018
- Network Representation Learning: A SurveyIEEE Transactions on Big Data, 2018
- Densely Connected Convolutional NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- node2vecPublished by Association for Computing Machinery (ACM) ,2016
- Community detection in social networksProceedings of the VLDB Endowment, 2015
- LINEPublished by Association for Computing Machinery (ACM) ,2015
- DeepWalkPublished by Association for Computing Machinery (ACM) ,2014
- E-rank: A Structural-Based Similarity Measure in Social NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012