Papers › Graph Convolutional Networks for Text Classification

Graph Convolutional Networks for Text Classification

15 Sep 2018arXiv:1809.05679archive 2025-07-28

Liang Yao, Chengsheng Mao, Yuan Luo

Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification. However, only a limited number of studies have explored the more flexible graph convolutional neural networks (convolution on non-grid, e.g., arbitrary graph) for the task. In this work, we propose to use graph convolutional networks for text classification. We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus. Our Text GCN is initialized with one-hot representation for word and document, it then jointly learns the embeddings for both words and documents, as supervised by the known class labels for documents. Our experimental results on multiple benchmark datasets demonstrate that a vanilla Text GCN without any external word embeddings or knowledge outperforms state-of-the-art methods for text classification. On the other hand, Text GCN also learns predictive word and document embeddings. In addition, experimental results show that the improvement of Text GCN over state-of-the-art comparison methods become more prominent as we lower the percentage of training data, suggesting the robustness of Text GCN to less training data in text classification.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (yao8839836/text_gcn) was not harvested; the 16 samples below come from 5 community repositories.

Syntology 16 code samples harvested from 5 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 16 samples from 5 repositories, 14 ran (10 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yao8839836/text_gcn officialmentioned in papertfSyntology: not harvested report
FoxerLee/TGCN mentioned on GitHubtfSyntology: not harvested report
chengsen/pytorch_textgcn mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (3 instrument-failed) · 0 unverified report
codeKgu/text-gcn mentioned on GitHubpytorchMITSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
dtriepke/Graph_Convolutional_Network mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
koreyou/text-gcn-chainer mentioned on GitHubpytorchCC0-1.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
plkmo/Bible_Text_GCN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ydtydr/hyla mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Random Laplacian Features for Learning with Hyperbolic Space (arXiv:2202.06854; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
yongbowin/Bible_Text_GCN_annotation mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

16 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
8ran
2unverified

Licence: 6 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

chengsen/pytorch_textgcn community (archive-listed) 4 samples, 4 ran (3 instrument-failed) · 0 unverified
cal_pmi build_graph.py ran · honoured contract no licence file found · pointer only · a5ebdf6ac2def3a0 · report fixture: signature W_ij:int/0/int, W:int/0/int, word_freq_1:int/0/int, word_freq_2:int/0/int · returned float · level recorded 2026-09-22
count_pmi build_graph.py ran · our draft was wrong no licence file found · pointer only · 23cb6c93ee0a7878 · report fixture: signature windows_len:int/0/int, word_pair_count:dict/0/?, word_window_freq:dict/0/?, threshold:float/0/float · returned list · level recorded 2026-09-22
get_window in 7 papers build_graph.py ran · our draft was wrong no licence file found · pointer only · a7642b4d294d07a6 · report fixture: signature content_lst:list/1/str, window_size:int/0/int · returned tuple · level recorded 2026-09-22
remove_less_word data_processor.py ran · our draft was wrong no licence file found · pointer only · 11c600e5158c8de1 · report fixture: signature lines_str:str/0/str, word_st:set/0/? · returned str · level recorded 2026-09-22
codeKgu/text-gcn community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
build_edges build_graph.py ran MIT (permissive) · d7c52fad2776eea6 · report fixture: signature doc_list:list/1/str, word_id_map:dict/0/?, vocab:dict/0/?, word_doc_freq:dict/0/?, window_size:int/0/int · returned csr_matrix · level recorded 2026-09-26
clean_doc in 6 papers prep_data.py ran fingerprinted MIT (permissive) · d3fab161b1ada8bb · report fixture: signature string:str/0/str, dataset:str/0/str · returned str · level recorded 2026-09-26
create_act model_text_gnn.py ran MIT (permissive) · f71177416c3999b7 · report fixture: signature act:str/0/str, num_parameters:NoneType/0/? · returned ReLU · level recorded 2026-09-26
get_vocab in 15 papers build_graph.py ran MIT (permissive) · f0aeffa095b44a3a · report fixture: signature text_list:list/1/str · returned defaultdict · level recorded 2026-09-26
proc_filepath utils.py ran fingerprinted MIT (permissive) · ca704301382f623d · report fixture: signature filepath:str/0/str, ext:str/0/str · returned str · level recorded 2026-09-26
clean_doc_ap prep_data.py unverified MIT (permissive) · 609ed2882449335b · report
clean_documents prep_data.py unverified MIT (permissive) · eef3ad654b28192f · report
dtriepke/Graph_Convolutional_Network community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
load_pickle in 115 papers model_train.py ran · our draft was wrong no licence file found · pointer only · d760f5d1c4f85eb6 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-22
koreyou/text-gcn-chainer community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
calc_pmi graphs.py ran CC0-1.0 (permissive) · b362ca4a14ece361 · report fixture: signature X:csr_matrix/2/float · returned csc_matrix · level recorded 2026-09-26
create_text_adjacency_matrix graphs.py ran CC0-1.0 (permissive) · 8439106958ba7d2c · report fixture: signature texts:list/1/list · returned coo_matrix · level recorded 2026-09-26
normalize_text in 60 papers nlp_utils.py ran fingerprinted CC0-1.0 (permissive) · 2950d6b582fe43a8 · report fixture: signature string:str/0/str · returned str · level recorded 2026-09-26
plkmo/Bible_Text_GCN community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
load_state in 19 papers text_GCN.py ran · honoured contract no licence file found · pointer only · 1d30b9a0ccf5a53d · report fixture: returned tuple · level recorded 2026-09-22

Tasks

General ClassificationSentiment AnalysisText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sentiment Analysis MR Text GCN Accuracy 76.74 #14 of 19 Archive leaderboard report
Text Classification 20NEWS Text GCN Accuracy 86.34 #10 of 16 Archive leaderboard report
Text Classification Ohsumed Text GCN Accuracy 68.36 #6 of 10 Archive leaderboard report
Text Classification R52 Text GCN Accuracy 93.56 #7 of 8 Archive leaderboard report
Text Classification R8 Text GCN Accuracy 97.07 #17 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

GCN

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