{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gresnet-graph-residuals-for-reviving-deep","title":"GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation","arxiv_id":"1909.05729","date":"2019-09-12","proceeding":null,"authors":["Jiawei Zhang","Lin Meng"],"abstract":"The existing graph neural networks (GNNs) based on the spectral graph convolutional operator have been criticized for its performance degradation, which is especially common for the models with deep architectures. In this paper, we further identify the suspended animation problem with the existing GNNs. Such a problem happens when the model depth reaches the suspended animation limit, and the model will not respond to the training data any more and become not learnable. Analysis about the causes of the suspended animation problem with existing GNNs will be provided in this paper, whereas several other peripheral factors that will impact the problem will be reported as well. To resolve the problem, we introduce the GResNet (Graph Residual Network) framework in this paper, which creates extensively connected highways to involve nodes' raw features or intermediate representations throughout the graph for all the model layers. Different from the other learning settings, the extensive connections in the graph data will render the existing simple residual learning methods fail to work. We prove the effectiveness of the introduced new graph residual terms from the norm preservation perspective, which will help avoid dramatic changes to the node's representations between sequential layers. Detailed studies about the GResNet framework for many existing GNNs, including GCN, GAT and LoopyNet, will be reported in the paper with extensive empirical experiments on real-world benchmark datasets.","url_abs":"https://arxiv.org/abs/1909.05729v2","url_pdf":"https://arxiv.org/pdf/1909.05729v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gresnet-graph-residuals-for-reviving-deep","repo_url":"https://github.com/anonymous-sourcecode/GResNet","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"gresnet-graph-residuals-for-reviving-deep","repo_url":"https://github.com/jwzhanggy/GResNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"gat","method_name":"GAT"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"GResNet(LoopyNet)","rank_in_archive_order":29,"of":71,"metrics":{"Accuracy":"73.7%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"GResNet(GAT)","rank_in_archive_order":32,"of":71,"metrics":{"Accuracy":"73.5%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"GResNet(GCN)","rank_in_archive_order":39,"of":71,"metrics":{"Accuracy":"72.7%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"LoopyNet","rank_in_archive_order":53,"of":71,"metrics":{"Accuracy":"71.6%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"GResNet(GAT)","rank_in_archive_order":22,"of":73,"metrics":{"Accuracy":"85.5%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"GResNet(GCN)","rank_in_archive_order":30,"of":73,"metrics":{"Accuracy":"84.3%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"GResNet(LoopyNet)","rank_in_archive_order":35,"of":73,"metrics":{"Accuracy":"83.9%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"LoopyNet","rank_in_archive_order":50,"of":73,"metrics":{"Accuracy":"82.6%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"GResNet(LoopyNet)","rank_in_archive_order":24,"of":70,"metrics":{"Accuracy":"83.0%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"GResNet(GAT)","rank_in_archive_order":26,"of":70,"metrics":{"Accuracy":"82.2%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"GResNet(GCN)","rank_in_archive_order":29,"of":70,"metrics":{"Accuracy":"81.7%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"LoopyNet","rank_in_archive_order":30,"of":70,"metrics":{"Accuracy":"81.2%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.05729","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}