Papers › DeepGCNs: Making GCNs Go as Deep as CNNs

DeepGCNs: Making GCNs Go as Deep as CNNs

15 Oct 2019arXiv:1910.06849archive 2025-07-28

Guohao Li, Matthias Müller, Guocheng Qian, Itzel C. Delgadillo, Abdulellah Abualshour, Ali Thabet, Bernard Ghanem

Convolutional Neural Networks (CNNs) have been very successful at solving a variety of computer vision tasks such as object classification and detection, semantic segmentation, activity understanding, to name just a few. One key enabling factor for their great performance has been the ability to train very deep networks. Despite their huge success in many tasks, CNNs do not work well with non-Euclidean data, which is prevalent in many real-world applications. Graph Convolutional Networks (GCNs) offer an alternative that allows for non-Eucledian data input to a neural network. While GCNs already achieve encouraging results, they are currently limited to architectures with a relatively small number of layers, primarily due to vanishing gradients during training. This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs. We show the benefit of using deep GCNs (with as many as 112 layers) experimentally across various datasets and tasks. Specifically, we achieve very promising performance in part segmentation and semantic segmentation on point clouds and in node classification of protein functions across biological protein-protein interaction (PPI) graphs. We believe that the insights in this work will open avenues for future research on GCNs and their application to further tasks not explored in this paper. The source code for this work is available at https://github.com/lightaime/deep_gcns_torch and https://github.com/lightaime/deep_gcns for PyTorch and TensorFlow implementation respectively.

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

Syntology 9 code samples: 8 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 9: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lightaime/deep_gcns_torch officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training Graph Neural Networks with 1000 Layers (arXiv:2106.07476; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
lightaime/deep_gcns officialmentioned in papertfMITSyntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified report
lightaime/deep_gcns_torch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training Graph Neural Networks with 1000 Layers (arXiv:2106.07476; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
lightaime/deep_gcns_torch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training Graph Neural Networks with 1000 Layers (arXiv:2106.07476; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

9 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 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.

1ran · our draft was wrong
4ran
4unverified

Licence: 1 of the 9 samples is 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 lightaime/deep_gcns. 1 sample is listed last, in a group without a repository. “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.

lightaime/deep_gcns official repository 8 samples, 4 ran (0 instrument-failed) · 4 unverified
get_points_colors_from_obj sem_seg/viz.py ran MIT (permissive) · b2906f9680613942 · report fixture: signature filename:str/0/str, limit:int/0/int · returned tuple · level recorded 2026-09-25
sample_data in 15 papers sem_seg/indoor3d_util.py ran fingerprinted MIT (permissive) · 5b5f8b1b747b7afa · report fixture: signature data:ndarray/2/float, num_sample:int/0/int · returned tuple · level recorded 2026-09-25
sample_data_label sem_seg/indoor3d_util.py ran fingerprinted MIT (permissive) · 8faf2ddce20e9709 · report fixture: signature data:ndarray/2/float, label:ndarray/1/int, num_sample:int/0/int · returned tuple · level recorded 2026-09-25
wrapped_partial in 12 papers sem_seg/batch_inference.py ran MIT (permissive) · 1e0de6b9c650bc32 · report fixture: signature func:callable/0/?, args:tuple/1/int, kwargs:dict/0/? · returned partial · level recorded 2026-09-25
dilated gcn_lib/tf_edge.py unverified MIT (permissive) · b7d5e1baa849c768 · report
get_max_relat_feature gcn_lib/tf_vertex.py unverified MIT (permissive) · a413566796454bf7 · report
max_relat_conv_layer gcn_lib/tf_vertex.py unverified MIT (permissive) · 5c13eeaa975af521 · report
room2blocks sem_seg/indoor3d_util.py unverified MIT (permissive) · 69af01e7fe976f9b · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_sampling_command repository not located ran · our draft was wrong licence of this copy not recorded · 7ffd07876c29c19b · report fixture: returned str · level recorded 2026-09-22

Tasks

3D Point Cloud Classification3D Semantic SegmentationNode ClassificationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ModelNet40 DeepGCN Mean Accuracy 90.9 #53 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 DeepGCN Number of params 2.2M #53 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 DeepGCN Overall Accuracy 93.6 #53 of 111 Archive leaderboard report
3D Semantic Segmentation PartNet DeepGCN mIOU 45.1 #5 of 6 Archive leaderboard report
Node Classification PPI DenseMRGCN-14 F1 99.43 #5 of 24 Archive leaderboard report
Node Classification PPI ResMRGCN-28 F1 99.41 #6 of 24 Archive leaderboard report
Semantic Segmentation S3DIS DeepGCN Mean IoU 60.0 #44 of 54 Archive leaderboard report
Semantic Segmentation S3DIS DeepGCN Number of params N/A #44 of 54 Archive leaderboard report
Semantic Segmentation S3DIS DeepGCN oAcc 85.9 #44 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 DeepGCN Number of params N/A #54 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 DeepGCN mIoU 52.49 #54 of 61 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

Graph Convolutional Networks

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