{"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/model-degradation-hinders-deep-graph-neural","title":"Model Degradation Hinders Deep Graph Neural Networks","arxiv_id":"2206.04361","date":"2022-06-09","proceeding":null,"authors":["Wentao Zhang","Zeang Sheng","Ziqi Yin","Yuezihan Jiang","Yikuan Xia","Jun Gao","Zhi Yang","Bin Cui"],"abstract":"Graph Neural Networks (GNNs) have achieved great success in various graph mining tasks.However, drastic performance degradation is always observed when a GNN is stacked with many layers. As a result, most GNNs only have shallow architectures, which limits their expressive power and exploitation of deep neighborhoods.Most recent studies attribute the performance degradation of deep GNNs to the \\textit{over-smoothing} issue. In this paper, we disentangle the conventional graph convolution operation into two independent operations: \\textit{Propagation} (\\textbf{P}) and \\textit{Transformation} (\\textbf{T}).Following this, the depth of a GNN can be split into the propagation depth ($D_p$) and the transformation depth ($D_t$). Through extensive experiments, we find that the major cause for the performance degradation of deep GNNs is the \\textit{model degradation} issue caused by large $D_t$ rather than the \\textit{over-smoothing} issue mainly caused by large $D_p$. Further, we present \\textit{Adaptive Initial Residual} (AIR), a plug-and-play module compatible with all kinds of GNN architectures, to alleviate the \\textit{model degradation} issue and the \\textit{over-smoothing} issue simultaneously. Experimental results on six real-world datasets demonstrate that GNNs equipped with AIR outperform most GNNs with shallow architectures owing to the benefits of both large $D_p$ and $D_t$, while the time costs associated with AIR can be ignored.","url_abs":"https://arxiv.org/abs/2206.04361v1","url_pdf":"https://arxiv.org/pdf/2206.04361v1.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":"model-degradation-hinders-deep-graph-neural","repo_url":"https://github.com/pku-dair/air","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"graph-mining","task_name":"Graph Mining"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.04361","atlas_url":"https://app.syntology.ai/?focus=2206.04361","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}