Papers › BertGCN: Transductive Text Classification by Combining GCN and BERT

BertGCN: Transductive Text Classification by Combining GCN and BERT

12 May 2021arXiv:2105.05727archive 2025-07-28

Yuxiao Lin, Yuxian Meng, Xiaofei Sun, Qinghong Han, Kun Kuang, Jiwei Li, Fei Wu

In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification. BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations. By jointly training the BERT and GCN modules within BertGCN, the proposed model is able to leverage the advantages of both worlds: large-scale pretraining which takes the advantage of the massive amount of raw data and transductive learning which jointly learns representations for both training data and unlabeled test data by propagating label influence through graph convolution. Experiments show that BertGCN achieves SOTA performances on a wide range of text classification datasets. Code is available at https://github.com/ZeroRin/BertGCN.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ZeroRin/BertGCN officialmentioned in papermentioned 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

Classification Text Classification Transductive Learning text-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Text Classification	20 Newsgroups	RoBERTaGCN	Accuracy	89.5	#1 of 1	Archive leaderboard	report
Text Classification	20NEWS	RoBERTaGCN	Accuracy	89.5	#2 of 16	Archive leaderboard	report
Text Classification	MR	RoBERTaGCN	Accuracy	89.7	#3 of 10	Archive leaderboard	report
Text Classification	Ohsumed	RoBERTaGCN	Accuracy	72.8	#1 of 10	Archive leaderboard	report
Text Classification	R52	1-6 BertGCN	Accuracy	96.6	#1 of 8	Archive leaderboard	report
Text Classification	R8	RoBERTaGCN	Accuracy	98.2	#4 of 21	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.

Methods

Adam Attention Attention Dropout BERT Dense Connections Dropout GCN Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

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