Papers › Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

30 Jun 2016NeurIPS 2016 12arXiv:1606.09375archive 2025-07-28

Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst

In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' embedding, represented by graphs. We present a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs. Importantly, the proposed technique offers the same linear computational complexity and constant learning complexity as classical CNNs, while being universal to any graph structure. Experiments on MNIST and 20NEWS demonstrate the ability of this novel deep learning system to learn local, stationary, and compositional features on graphs.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1606.09375")

Code

Syntology Ran 2 of 6 code samples harvested from 4 repositories linked to this paper; 4 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 0 ran; community (archive-listed): 4 samples from 3 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mdeff/cnn_graph officialmentioned in papermentioned on GitHubtf report
ajbisberg/gcn mentioned on GitHubtf report
hazdzz/ChebyNet mentioned on GitHubpytorch report
mdeff/paper-cnn-graph-nips2016 mentioned on GitHubCC-BY-4.0 report
selmiss/gp-tlstgcn 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

6 samples harvested; 2 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran
4unverified

Licence: 2 of the 6 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 4 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

base_model mdeff/cnn_graph/lib/models.py official repository unverified MIT (permissive) · fcd0e1963d1c958e · report
cgcnn2_2 mdeff/cnn_graph/lib/models.py official repository unverified MIT (permissive) · 9cb375d9b8adcbdf · report
ChebGraphConv hazdzz/ChebyNet/model/layers.py community (archive-listed) ran LGPL-2.1 (copyleft) · pointer only · 030e43e156dbda0e · report
ChebGraphConv selmiss/gp-tlstgcn/model/layers.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted LGPL-2.1 (copyleft) · pointer only · c6ca6754d762f682 · report
GraphConvolution ajbisberg/gcn/gcn/layers.py community (archive-listed) unverified MIT (permissive) · d033d441612bfa4b · report
Layer ajbisberg/gcn/gcn/layers.py community (archive-listed) unverified MIT (permissive) · e643d1f9db59f99c · report

Tasks

Node ClassificationSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Property Prediction ogbg-molpcba ChebNet Ext. data No #32 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba ChebNet Number of params 1475003 #32 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba ChebNet Test AP 0.2306 ± 0.0016 #32 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba ChebNet Validation AP 0.2372 ± 0.0018 #32 of 36 Archive leaderboard report
Node Classification CiteSeer (0.5%) ChebyNet Accuracy 45.3% #10 of 14 Archive leaderboard report
Node Classification CiteSeer (1%) ChebyNet Accuracy 59.4% #10 of 14 Archive leaderboard report
Node Classification CiteSeer with Public Split: fixed 20 nodes per class ChebyNet Accuracy 70.1% #33 of 40 Archive leaderboard report
Node Classification Citeseer ChebNet Accuracy 69.8% #60 of 71 Archive leaderboard report
Node Classification Cora ChebNet Accuracy 81.2% #62 of 73 Archive leaderboard report
Node Classification Cora (0.5%) ChebyNet Accuracy 33.9% #15 of 15 Archive leaderboard report
Node Classification Cora (1%) ChebyNet Accuracy 44.2% #15 of 15 Archive leaderboard report
Node Classification Cora (3%) ChebyNet Accuracy 62.1% #14 of 15 Archive leaderboard report
Node Classification Cora with Public Split: fixed 20 nodes per class ChebyNet Accuracy 78.0% #33 of 36 Archive leaderboard report
Node Classification PubMed (0.03%) ChebyNet Accuracy 45.3% #14 of 14 Archive leaderboard report
Node Classification PubMed (0.05%) ChebyNet Accuracy 48.2% #14 of 14 Archive leaderboard report
Node Classification PubMed (0.1%) ChebyNet Accuracy 55.2% #14 of 14 Archive leaderboard report
Node Classification PubMed with Public Split: fixed 20 nodes per class ChebyNet Accuracy 69.8% #37 of 37 Archive leaderboard report
Node Classification Pubmed ChebNet Accuracy 74.4% #64 of 70 Archive leaderboard report
Skeleton Based Action Recognition SBU / SBU-Refine ChebyNet Accuracy 96.00% #4 of 9 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

Introduced by this paper: ChebNet

ChebNet

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