Methods › Graphs › Graph Models › GCNII
GCNII
Introduced by Ming Chen et al. in Simple and Deep Graph Convolutional Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
GCNII is an extension of a Graph Convolution Networks 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.
Papers archive 2025-07-28
7 shown of 7, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Understanding and Improving Deep Graph Neural Networks: A Probabilistic Graphical Model Perspective 25 Jan 2023 · 0 repositories · arXiv:2301.10536
-
Multi-duplicated Characterization of Graph Structures using Information Gain Ratio for Graph Neural Networks 24 Dec 2022 · 0 repositories · arXiv:2212.12691
-
Every Node Counts: Improving the Training of Graph Neural Networks on Node Classification 29 Nov 2022 · 0 repositories · arXiv:2211.16631
-
wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction 21 Sep 2021 · 0 repositories · arXiv:2109.11519
-
Layer-wise Adaptive Graph Convolution Networks Using Generalized Pagerank 24 Aug 2021 · 0 repositories · arXiv:2108.10636
-
Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework 4 Mar 2021 · 1 repository · arXiv:2103.02885Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
-
Simple and Deep Graph Convolutional Networks 4 Jul 2020 · 4 repositories · arXiv:2007.02133Syntology ran 5 of 7 samples · 2 unverified · 4 pointer-only (licence)
Tasks archive 2025-07-28
13 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections