ChebNet: localized polynomial graph filtering without eigendecomposition

What changed

Parameterized graph filters as truncated Chebyshev polynomials of the Laplacian, evaluating them by sparse recurrence and combining graph coarsening with efficient pooling.

Scientific scope

Parameterized graph filters as truncated Chebyshev polynomials of the Laplacian, evaluating them by sparse recurrence and combining graph coarsening with efficient pooling. Inherits polynomial graph signal processing and spectral CNNs. Filtering costs scale with polynomial order and graph edges, not constant cost on arbitrary dense graphs; full layer costs include feature channels.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits polynomial graph signal processing and spectral CNNs. Filtering costs scale with polynomial order and graph edges, not constant cost on arbitrary dense graphs; full layer costs include feature channels.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction