Papers › SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels

SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels

24 Nov 2017CVPR 2018 6arXiv:1711.08920archive 2025-07-28

Matthias Fey, Jan Eric Lenssen, Frank Weichert, Heinrich Müller

We present Spline-based Convolutional Neural Networks (SplineCNNs), a variant of deep neural networks for irregular structured and geometric input, e.g., graphs or meshes. Our main contribution is a novel convolution operator based on B-splines, that makes the computation time independent from the kernel size due to the local support property of the B-spline basis functions. As a result, we obtain a generalization of the traditional CNN convolution operator by using continuous kernel functions parametrized by a fixed number of trainable weights. In contrast to related approaches that filter in the spectral domain, the proposed method aggregates features purely in the spatial domain. In addition, SplineCNN allows entire end-to-end training of deep architectures, using only the geometric structure as input, instead of handcrafted feature descriptors. For validation, we apply our method on tasks from the fields of image graph classification, shape correspondence and graph node classification, and show that it outperforms or pars state-of-the-art approaches while being significantly faster and having favorable properties like domain-independence.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

rusty1s/pytorch_geometric officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to How Attentive are Graph Attention Networks? (arXiv:2105.14491; that paper's own run record: 11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
MikelBros/Deep_Spammer_Detection_GCN mentioned on GitHubpytorchSyntology: not harvested report
mikel-brostrom/Deep_Spammer_Detection_GCN mentioned on GitHubpytorchSyntology: not harvested report
rusty1s/pytorch_spline_conv mentioned on GitHubpytorchSyntology: not harvested report
abhilash1910/SpectralEmbeddings tfNOASSERTIONSyntology: 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deep LearningGeneral ClassificationGraph ClassificationNode ClassificationSuperpixel Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Citeseer SplineCNN Accuracy 79.20% #7 of 71 Archive leaderboard report
Node Classification Cora SplineCNN Accuracy 89.48% ± 0.31% #2 of 73 Archive leaderboard report
Node Classification Pubmed SplineCNN Accuracy 88.88% #13 of 70 Archive leaderboard report
Superpixel Image Classification 75 Superpixel MNIST SplineCNN Classification Error 4.78 #5 of 6 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

Convolution

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