AI Paper Atlas

Research map / Graph learning / GNN architectures

Deep Message Passing on Sets

Yifeng Shi, Junier Oliva, Marc Niethammer

AAAI 2020 · Graph learning › GNN architectures · approach: Expressive equivariant message passing · 6 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
replace the learned latent graph with a uniform graph (ablation)V-DMPS · Counting unique characterstest accuracy: 0.6446 ± 0.0174 -> 0.1357 ± 0.0000Hurt
replace the learned latent graph with a uniform graph (ablation)D-DMPS w/ LDC · Counting unique characterstest accuracy: 0.6674 ± 0.0080 -> 0.4661 ± 0.0085Hurt
add set-residual blocks (ablation)DMPS · Counting unique characterstest accuracy: 0.6446 ± 0.0174 -> 0.6600 ± 0.0103Improved
add set-denoising blocks with fixed diffusion coefficient (ablation)DMPS · Counting unique characterstest accuracy: 0.6446 ± 0.0174 -> 0.6748 ± 0.0120Improved
add set-denoising blocks with learnable diffusion coefficient (ablation)DMPS · Counting unique characterstest accuracy: 0.6446 ± 0.0174 -> 0.6674 ± 0.0080Improved
set the diffusion coefficient too high or too low (ablation)D-DMPS w/ FDC · ModelNet40, 100 pointstest accuracyHurt
add set-residual blocks (ablation)DMPS · ModelNet40, 100 pointstest accuracy: 0.8367 ± 0.0047 -> 0.8475 ± 0.0036Improved
add set-denoising blocks (ablation)DMPS · ModelNet40, 100 pointstest accuracy: 0.8367 ± 0.0047 -> 0.8571 ± 0.0062Improved
add set-residual blocks (ablation)DMPS · ModelNet40, 1000 pointstest accuracy: 0.8751 ± 0.0029 -> 0.8935 ± 0.0016Improved
add set-denoising blocks (ablation)DMPS · ModelNet40, 1000 pointstest accuracy: 0.8751 ± 0.0029 -> 0.8798 ± 0.0020Improved
add set-residual blocks (ablation)DMPS · Breast Cancertest accuracy: 0.800 ± 0.023 -> 0.818 ± 0.029Improved
add set-denoising blocks (ablation)DMPS · Breast Cancertest accuracy: 0.800 ± 0.023 -> 0.846 ± 0.019Improved

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