Hacker News
- Beyond message passing: A physics-inspired paradigm for graph neural networks https://thegradient.pub/graph-neural-networks-beyond-message-passing-and-weisfeiler-lehman/ 16 comments
Linked pages
- [1512.03547] Graph Isomorphism in Quasipolynomial Time http://arxiv.org/abs/1512.03547 31 comments
- The Future of Deep Learning Is Photonic - IEEE Spectrum https://spectrum.ieee.org/the-future-of-deep-learning-is-photonic 26 comments
- Transformers are Graph Neural Networks https://thegradient.pub/transformers-are-graph-neural-networks/ 25 comments
- [2104.13478] Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges https://arxiv.org/abs/2104.13478 16 comments
- Using Subgraphs for More Expressive GNNs | by Michael Bronstein | Towards Data Science https://towardsdatascience.com/using-subgraphs-for-more-expressive-gnns-8d06418d5ab?sk=8806ffcd9ecf74c440d40df53528c1c7 6 comments
- ICLR 2021 Keynote - "Geometric Deep Learning: The Erlangen Programme of ML" - M Bronstein - YouTube https://www.youtube.com/watch?v=w6Pw4MOzMuo 1 comment
- [2006.11287] Discovering Symbolic Models from Deep Learning with Inductive Biases https://arxiv.org/abs/2006.11287 0 comments
Related searches:
Search whole site: site:thegradient.pub
Search title: Beyond Message Passing: a Physics-Inspired Paradigm for Graph Neural Networks
See how to search.