AI Paper Atlas

Research map / Graph learning / GNN architectures

Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering

Mingqi Yang, Wenjie Feng, Yanming Shen, Bryan Hooi

ICML 2023 · Graph learning › GNN architectures · approach: Spectral GNN design · 0 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
learnable decomposition (eps,k) instead of fixed Laplacian, with linear filter (channel-shared) (ablation)PDF shd · ZINCtest MAE: 0.219 -> 0.167Improved
learnable decomposition (eps,k) instead of fixed Laplacian, with linear filter (channel-independent) (ablation)PDF idp · ZINCtest MAE: 0.172 -> 0.150Improved
more expressive f (Lin -> 1-layer -> 2-layer MLP) (ablation)PDF idp · ZINCtest MAE: 0.150 -> 0.088 -> 0.066Improved
more expressive f (Lin -> 1-layer -> 2-layer MLP) (ablation)PDF shd · ZINCtest MAE: 0.167 -> 0.160 -> 0.112Improved
restrict representations to 2-hop sparse subspace (ablation)PDF idp 2L · ZINCtest MAE: 0.066 -> 0.111Hurt
channel-independent (idp) instead of channel-shared (shd) decomposition/filtering (ablation)PDF 2L · ZINCtest MAE: 0.112 (shd) -> 0.066 (idp)Improved
PDF (idp, 2-layer MLP, learnable decomposition) vs. GCN/GIN baselinesPDF · ZINCtest MAE: 0.066 vs GPS 0.070, GIN 0.526Improved
PDF vs. GPS on ogbg-ppa (sparse 1-hop subspace)PDF · ogbg-ppaACC (%): 80.10 vs 80.15No clear effect
PDF on TUDataset, 6 of 8 datasets best accuracyPDF · TUDatasetaccuracy (%): best on NCI1, NCI109, ENZYMES, PTC_MR, IMDB-B, RDT-B; not MUTAG (FGSD 92.12) or PROTEINS (DiffPool 78.1)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy