Papers
Topics
Authors
Recent
Search
2000 character limit reached

Entropy Aware Message Passing in Graph Neural Networks

Published 7 Mar 2024 in cs.LG | (2403.04636v1)

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (17)
  1. Grand: Graph neural diffusion. In International Conference on Machine Learning, pp.  1407–1418. PMLR, 2021.
  2. Simple and deep graph convolutional networks. In International conference on machine learning, pp.  1725–1735. PMLR, 2020.
  3. Graph neural networks for social recommendation. In The world wide web conference, pp.  417–426, 2019.
  4. Citeseer: An automatic citation indexing system. In Proceedings of the third ACM conference on Digital libraries, pp.  89–98, 1998.
  5. Simple gnn regularisation for 3d molecular property prediction & beyond. arXiv preprint arXiv:2106.07971, 2021.
  6. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905, 2018.
  7. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  770–778, 2016.
  8. Deepgcns: Can gcns go as deep as cnns? In Proceedings of the IEEE/CVF international conference on computer vision, pp.  9267–9276, 2019.
  9. Automating the construction of internet portals with machine learning. Information Retrieval, 3:127–163, 2000.
  10. Rankme: Reliable human ratings for natural language generation. arXiv preprint arXiv:1803.05928, 2018.
  11. Gradient gating for deep multi-rate learning on graphs. arXiv preprint arXiv:2210.00513, 2022.
  12. A survey on oversmoothing in graph neural networks. arXiv preprint arXiv:2303.10993, 2023.
  13. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  14. Acmp: Allen-cahn message passing for graph neural networks with particle phase transition. arXiv preprint arXiv:2206.05437, 2022.
  15. Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking. Nature Communications, 14(1):2585, May 2023. ISSN 2041-1723. doi: 10.1038/s41467-023-38192-3. URL https://doi.org/10.1038/s41467-023-38192-3.
  16. Pairnorm: Tackling oversmoothing in gnns. arXiv preprint arXiv:1909.12223, 2019.
  17. Dirichlet energy constrained learning for deep graph neural networks. Advances in Neural Information Processing Systems, 34:21834–21846, 2021.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.