AI Paper Atlas

Research map / Graph learning / GNN architectures

Generalised Implicit Neural Representations

Daniele Grattarola, Pierre Vandergheynst

NeurIPS 2022 · Graph learning › GNN architectures · approach: Theory of graph convolutional networks · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
Use spectral embeddings of the graph as INR input instead of node coordinates (ReLU activation)INR · Bunny held-out R^2R^2: 0.000 -> 0.932Improved
Use spectral embeddings instead of node coordinates (ReLU activation)INR · Protein held-out R^2R^2: 0.799 -> 0.921Improved
Use spectral embeddings instead of node coordinates (SIREN activation)INR · Protein held-out R^2R^2: 0.275 -> 0.916Improved
Use spectral embeddings instead of node coordinates (SIREN activation)INR · Bunny held-out R^2R^2: 0.919 -> 0.885Hurt
Reduce spectral embedding size to k<=3 (ablation)Generalised INR · BunnyR^2Hurt
Use large spectral embedding size k=100 (ablation)Generalised INR · BunnyR^2Improved
Use smaller k and ReLU activations to improve transfer to new graph realisationsGeneralised INR · Transferabilitytransfer qualityImproved
Increase k in super-resolution transfer (ablation)Generalised INR · Bunny super-resolutionR^2Mixed
Ignore nodes above 90th percentile of squared error in super-resolution evaluationGeneralised INR · Bunny super-resolutionR^2: 0.39 -> 0.94Improved
Larger latent size z in multi-protein autodecoder (ablation)Conditional GINR · Multi-protein INRR^2No clear effect
Increase number of proteins in the dataset (ablation)Conditional GINR · Multi-protein INRR^2Hurt
Use different Laplacian normalisation for spectral embeddings (ablation)Generalised INR · AppendixperformanceNo clear effect

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