Please use this identifier to cite or link to this item:
Title: Poisson kernel: avoiding self-smoothing in graph convolutional networks
Authors: Yang, Ziqing
Han, Shoudong
Zhao, Jun
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Source: Yang, Z., Han, S. & Zhao, J. (2022). Poisson kernel: avoiding self-smoothing in graph convolutional networks. Pattern Recognition, 124, 108443-.
Journal: Pattern Recognition
Abstract: Graph convolutional network is now an effective tool to deal with non-Euclidean data, such as social behavior analysis, molecular structure analysis, and skeleton-based action recognition. Graph convolutional kernel is one of the most significant factors in graph convolutional networks to extract nodes’ feature, and some variants of it have achieved highly satisfactory performance theoretically and experimentally. However, there was limited research about how exactly different graph structures influence the performance of these kernels. Some existing methods used an adaptive convolutional kernel to deal with a given graph structure, which still not explore the internal reasons. In this paper, we start from theoretical analysis of the spectral graph and study the properties of existing graph convolutional kernels, revealing the self-smoothing phenomenon and its effect in specific structured graphs. After that, we propose the Poisson kernel that can avoid self-smoothing without training any adaptive kernel. Experimental results demonstrate that our Poisson kernel not only works well on the benchmark datasets where state-of-the-art methods work fine, but also is evidently superior to them in synthetic datasets.
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2021.108443
Rights: © 2021 Elsevier Ltd. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Citations 50

Updated on Nov 23, 2022

Web of ScienceTM
Citations 50

Updated on Nov 18, 2022

Page view(s)

Updated on Nov 25, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.