Papers › BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation

BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation

21 Jun 2021NeurIPS 2021 12arXiv:2106.10994archive 2025-07-28

Mingguo He, Zhewei Wei, Zengfeng Huang, Hongteng Xu

Many representative graph neural networks, e.g., GPR-GNN and ChebNet, approximate graph convolutions with graph spectral filters. However, existing work either applies predefined filter weights or learns them without necessary constraints, which may lead to oversimplified or ill-posed filters. To overcome these issues, we propose BernNet, a novel graph neural network with theoretical support that provides a simple but effective scheme for designing and learning arbitrary graph spectral filters. In particular, for any filter over the normalized Laplacian spectrum of a graph, our BernNet estimates it by an order-K Bernstein polynomial approximation and designs its spectral property by setting the coefficients of the Bernstein basis. Moreover, we can learn the coefficients (and the corresponding filter weights) based on observed graphs and their associated signals and thus achieve the BernNet specialized for the data. Our experiments demonstrate that BernNet can learn arbitrary spectral filters, including complicated band-rejection and comb filters, and it achieves superior performance in real-world graph modeling tasks. Code is available at https://github.com/ivam-he/BernNet.

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="2106.10994")

Code

Syntology Ran 0 of 1 code samples harvested from 1 repository linked to this paper; 1 has no recorded run.

By repository: official repository: 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ivam-he/BernNet 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

1 sample harvested; 0 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1unverified

Licence: 1 of the 1 sample 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 ivam-he/BernNet. “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.

BernConv ivam-he/BernNet/LearningFilters/Bern.py official repository unverified no licence file found · pointer only · 7f78c43b41f89607 · report

Tasks

GPRGraph Neural NetworkNode ClassificationNode Classification on Non-Homophilic (Heterophilic) Graphs

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Chameleon (60%/20%/20% random splits) BernNet 1:1 Accuracy 68.29 ± 1.58 #11 of 38 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) BernNet 1:1 Accuracy 80.09 ± 0.79 #22 of 33 Archive leaderboard report
Node Classification Cora (60%/20%/20% random splits) BernNet 1:1 Accuracy 88.52 ± 0.95 #19 of 33 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) BernNet 1:1 Accuracy 92.13 ± 1.64 #15 of 36 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) BernNet 1:1 Accuracy 41.79 ± 1.01 #7 of 37 Archive leaderboard report
Node Classification PubMed (60%/20%/20% random splits) BernNet 1:1 Accuracy 88.48 ± 0.41 #27 of 37 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) BernNet 1:1 Accuracy 51.35 ± 0.73 #14 of 37 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) BernNet 1:1 Accuracy 93.12 ± 0.65 #14 of 36 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon(60%/20%/20% random splits) BernNet 1:1 Accuracy 68.29 ± 1.58 #8 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) BernNet 1:1 Accuracy 92.13 ± 1.64 #15 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) BernNet 1:1 Accuracy 93.12 ± 0.65 #13 of 32 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

ChebNetGraph Neural Network

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