Article

Oversmoothing as Disagreement Contraction inMessage-Passing Graph Neural Networks

2026-04-28

Abstract excerpt

<title>Abstract</title> <p>Oversmoothing is a central limitation of deep message-passing Graph NeuralNetworks (GNNs), wherein node representations become increasingly indistinguishable as depth grows and downstream discrimination deteriorates. Thispaper studies oversmoothing for a fixed-diffusion subclass of message-passingarchitectures, with random-walk diffusion P = D−1A on undirected graphsas the primary case;...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: a45177b7-440e-59a8-9dcb-476749ea632e
DOI: 10.21203/rs.3.rs-9446792/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 8 closest

Oversmoothing as Disagreement Contraction inMessage-Passing Graph Neural NetworksDOI 10.21203/rs.3.rs-9446792/v1Read

Energy–Bridge Transfer Law: A Quantitative Bridge Between Topology and Dynamics in Graph SystemsSemantic proximity Read

MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information LeakageSemantic proximity Read

BioGraph-SentiCOVID: Calibrated Adaptive Context Selection for Graph Neural Sentiment Analysis of COVID-19 TweetsSemantic proximity Read

What Makes Neural Networks Trainable? Invexity as a Structural Design Principle in AISemantic proximity Read

MeanRadius SMOTE Based Graph Neural Network for Imbalanced Node Classification in Fault and Intrusion DetectionSemantic proximity Read

Backpropagation-Free Continual Learning: A Unified Energy-Based Framework, Reproducible Benchmark, and Open ChallengesSemantic proximity Read

Modeling Multi-Modal Brain Connectomes for Brain Disorder Diagnosis via Graph Diffusion Optimal Transport NetworkSemantic proximity Read

Beyond Deep Learning—Space, Time, and EmergenceSemantic proximity Read