mlsanityData to 14 Oct 2026

Entropy Aware Message Passing in Graph Neural Networks

arXiv 2403.04636 ↗First posted 7 Mar 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Graph Neural Networks struggle with oversmoothing. This paper introduces a novel, physics-inspired GNN model designed to mitigate this issue. Our approach integrates with existing GNN architectures, introducing an entropy-aware message passing term. This term performs gradient ascent on the entropy during node aggregation, thereby preserving a certain degree of entropy in the embeddings. We conduct a comparative analysis of our model against state-of-the-art GNNs across various common datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 17 references that are in the map. First posted on arXiv 7 Mar 2024.

Builds on

12 of 17 references.

References · 12

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  4. 2020Simple and Deep Graph Convolutional Networkscited by 860
  5. 2019Graph Neural Networks for Social Recommendationcited by 714
  6. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  7. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  8. 2021GRAND: Graph Neural Diffusioncited by 258
  9. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 247
  10. 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
  11. 2022Gradient Gating for Deep Multi-Rate Learning on Graphscited by 49
  12. 2021Simple GNN Regularisation for 3D Molecular Property Prediction & Beyondcited by 44

Built on by

Not cited yet.