AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Learning on Arbitrary Graph Topologies via Predictive Coding

Tommaso Salvatori, Luca Pinchetti, Beren Millidge, Yuhang Song, Tianyi Bao, Rafal Bogacz, Thomas Lukasiewicz

NeurIPS 2022 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 13 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 a fully connected PC graph instead of the tested fully connected baselinesMNIST classification · MNISTtest accuracy: 91.76 $\pm$ 0.02 % vs 79.23 $\pm$ 0.15 %Improved
Use a fully connected PC graph instead of the tested fully connected baselinesFashionMNIST classification · FashionMNISTtest accuracy: 83.72 $\pm$ 0.33 % vs 69.63 $\pm$ 1.64 %Improved
Use a fully connected PC graph instead of the tested fully connected baselinesSVHN classification · SVHNtest accuracy: 84.51 $\pm$ 0.11 % vs 59.14 $\pm$ 2.64 %Improved
Train a multilayer PCN rather than a BP multilayer perceptronMNIST classification · MNISTtest accuracy: 98.47 $\pm$ 0.12 vs 98.41 $\pm$ 0.18No clear effect
Train a multilayer PCN rather than a BP multilayer perceptronFashionMNIST classification · FashionMNISTtest accuracy: 89.92 $\pm$ 0.23 vs 90.29 $\pm$ 0.33No clear effect
Train a multilayer PCN rather than a BP multilayer perceptronSVHN classification · SVHNtest accuracy: 88.99 $\pm$ 0.26 vs 89.31 $\pm$ 0.09No clear effect
Train a multilayer PCN rather than a BP multilayer perceptronCIFAR10 classification · CIFAR10test accuracy: 56.23 $\pm$ 3.36 vs 59.11 $\pm$ 2.47Hurt
Add hierarchical structure instead of using a fully connected PC graph (ablation)PC graphs on generation tasks · MNIST and FashionMNIST generationgeneration qualityImproved
Add recurrent connections to a feedforward PC graph (ablation)PC graphs reconstructing noisy or unfamiliar inputs · MNIST reconstructionreconstruction qualityImproved
Add extra feedforward layers beyond the tested best-depth range (ablation)Feedforward PC graph · Generation tasksconvergence timeHurt
Increase feedforward network width beyond the best-performing width (ablation)Feedforward PC graph · Generation tasksgeneration qualityHurt
Add strong weight decay rather than use low weight decay (ablation)Recurrent PC graph · MNIST conditional reconstruction with labelsreconstruction qualityImproved

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