Papers › Residual Network and Embedding Usage: New Tricks of Node Classification with Graph...

Residual Network and Embedding Usage: New Tricks of Node Classification with Graph Convolutional Networks

18 May 2021arXiv:2105.08330archive 2025-07-28

Huixuan Chi, Yuying Wang, Qinfen Hao, Hong Xia

Graph Convolutional Networks (GCNs) and subsequent variants have been proposed to solve tasks on graphs, especially node classification tasks. In the literature, however, most tricks or techniques are either briefly mentioned as implementation details or only visible in source code. In this paper, we first summarize some existing effective tricks used in GCNs mini-batch training. Based on this, two novel tricks named GCN_res Framework and Embedding Usage are proposed by leveraging residual network and pre-trained embedding to improve baseline's test accuracy in different datasets. Experiments on Open Graph Benchmark (OGB) show that, by combining these techniques, the test accuracy of various GCNs increases by 1.21%~2.84%. We open source our implementation at https://github.com/ytchx1999/PyG-OGB-Tricks.

PaperPDFCode

Code

ytchx1999/PyG-OGB-Tricks officialmentioned in papermentioned on GitHubpytorch report
ytchx1999/GCN_res-CS-v2 mentioned on GitHubpytorch report
ytchx1999/PyG-OGB-Tricks mentioned on GitHubpytorch report
ytchx1999/PyG-OGB-Tricks mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Node ClassificationNode Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Property Prediction ogbn-arxiv GAT-node2vec + BoT + self-KD Ext. data No #23 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT-node2vec + BoT + self-KD Number of params 1700432 #23 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT-node2vec + BoT + self-KD Test Accuracy 0.7420 ± 0.0004 #23 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT-node2vec + BoT + self-KD Validation Accuracy 0.7482 ± 0.0015 #23 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT-node2vec + BoT Ext. data No #28 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT-node2vec + BoT Number of params 1700432 #28 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT-node2vec + BoT Test Accuracy 0.7405 ± 0.0004 #28 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT-node2vec + BoT Validation Accuracy 0.7482 ± 0.0015 #28 of 86 Archive leaderboard report
Node Property Prediction ogbn-mag R-GSN + metapath2vec Ext. data No #24 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag R-GSN + metapath2vec Number of params 309777252 #24 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag R-GSN + metapath2vec Test Accuracy 0.5109 ± 0.0038 #24 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag R-GSN + metapath2vec Validation Accuracy 0.5295 ± 0.0042 #24 of 39 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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