{"url":"/method/gcnii","slug":"gcnii","name":"GCNII","full_name":"GCNII","full_name_withheld":false,"description_markdown":"**GCNII** is an extension of a [Graph Convolution Networks](https://www.paperswithcode.com/method/gcn) with two new techniques, initial residual and identify mapping, to tackle the problem of oversmoothing -- where stacking more layers and adding non-linearity tends to degrade performance. At each layer, initial residual constructs a skip connection from the input layer, while identity mapping adds an identity matrix to the weight matrix.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Simple and Deep Graph Convolutional Networks","paper":"/paper/simple-and-deep-graph-convolutional-networks-1","first_author":"Ming Chen","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/simple-and-deep-graph-convolutional-networks-1"},"source":{"url":"https://arxiv.org/abs/2007.02133v1","title":"Simple and Deep Graph Convolutional Networks","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Graphs","area_id":"graphs","collection":"Graph Models","url":"/methods/category/graph-models","pwc_aliases":[]}],"n_papers_tagged":7,"archive_num_papers":7,"papers_newest_first":[{"paper":null,"title":"Understanding and Improving Deep Graph Neural Networks: A Probabilistic Graphical Model Perspective","date":"2023-01-25","arxiv_id":"2301.10536","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-duplicated Characterization of Graph Structures using Information Gain Ratio for Graph Neural Networks","date":"2022-12-24","arxiv_id":"2212.12691","n_code_links":0,"syntology":null},{"paper":null,"title":"Every Node Counts: Improving the Training of Graph Neural Networks on Node Classification","date":"2022-11-29","arxiv_id":"2211.16631","n_code_links":0,"syntology":null},{"paper":null,"title":"wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction","date":"2021-09-21","arxiv_id":"2109.11519","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-and-interpretable-graph-convolution","title":"Layer-wise Adaptive Graph Convolution Networks Using Generalized Pagerank","date":"2021-08-24","arxiv_id":"2108.10636","n_code_links":0,"syntology":null},{"paper":"/paper/extract-the-knowledge-of-graph-neural","title":"Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework","date":"2021-03-04","arxiv_id":"2103.02885","n_code_links":1,"syntology":{"ran":2,"of":3,"unverified":1,"pointer_only":3}},{"paper":"/paper/simple-and-deep-graph-convolutional-networks-1","title":"Simple and Deep Graph Convolutional Networks","date":"2020-07-04","arxiv_id":"2007.02133","n_code_links":4,"syntology":{"ran":5,"of":7,"unverified":2,"pointer_only":4}}],"papers_shown":7,"tasks":[{"task":"/task/node-classification","name":"Node Classification","papers":5},{"task":"/task/link-prediction","name":"Link Prediction","papers":2},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/generalization-bounds","name":"Generalization Bounds","papers":1},{"task":"/task/graph-attention","name":"Graph Attention","papers":1},{"task":"/task/graph-classification","name":"Graph Classification","papers":1},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":1},{"task":"/task/graph-regression","name":"Graph Regression","papers":1},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":1},{"task":"/task/link-sign-prediction","name":"Link Sign Prediction","papers":1},{"task":"/task/node-classification-on-non-homophilic","name":"Node Classification on Non-Homophilic (Heterophilic) Graphs","papers":1},{"task":"/task/node-property-prediction","name":"Node Property Prediction","papers":1},{"task":"/task/variational-inference","name":"Variational Inference","papers":1}],"tasks_shown":13,"n_tasks":13,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":3},{"year":"2022","papers":2},{"year":"2023","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/gcnii"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}