P-Tensors: a General Formalism for Constructing Higher Order Message Passing Networks
Not on the map. Why?
Abstract (arXiv)
Several recent papers have proposed increasing the expressive power of graph neural networks by exploiting subgraphs or other topological structures. In parallel, researchers have investigated higher order permutation equivariant networks. In this paper we tie these two threads together by providing a general framework for higher order permutation equivariant message passing in subgraph neural networks. In this paper we introduce a new type of mathematical object called P-tensors, which provide a simple way to define the most general form of permutation equivariant message passing in both the above two categories of networks. We show that the P-Tensors paradigm can achieve state-of-the-art performance on benchmark molecular datasets.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 38 of its 59 references that are in the map. First posted on arXiv 19 Jun 2023.
Builds on
38 of 59 references.
References · 38
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2017Deep Setscited by 1,421
- 2019Strategies for Pre-training Graph Neural Networkscited by 971
- 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
- 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
- 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
26 more
- 2018Hypergraph Neural Networkscited by 488
- 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
- 2019Provably Powerful Graph Networkscited by 389
- 2018Invariant and Equivariant Graph Networkscited by 346
- 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
- 2015Diffusion-Convolutional Neural Networkscited by 268
- 2020Can Graph Neural Networks Count Substructures?cited by 236
- 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
- 2021Identity-aware Graph Neural Networkscited by 198
- 2019Universal Invariant and Equivariant Graph Neural Networkscited by 183
- 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 155
- 2021Equivariant Subgraph Aggregation Networkscited by 154
- 2019On the Universality of Invariant Networkscited by 152
- 2019Relational Pooling for Graph Representationscited by 150
- 2022Understanding and Extending Subgraph GNNs by Rethinking Their Symmetriescited by 112
- 2020Simplicial Neural Networkscited by 110
- 2020HNHN: Hypergraph Networks with Hyperedge Neuronscited by 109
- 2020Subgraph Neural Networkscited by 73
- 2020Hierarchical Inter-Message Passing for Learning on Molecular Graphscited by 59
- 2021Autobahn: Automorphism-based Graph Neural Netscited by 39
- 2020Natural Graph Networkscited by 35
- 2019Universal approximations of permutation invariant/equivariant functions by deep neural networkscited by 29
- 2020The general theory of permutation equivarant neural networks and higher order graph variational encoderscited by 28
- 2019GSN: A Graph-Structured Network for Multi-Party Dialoguescited by 26
- 2021Topological Signal Processing over Cell Complexescited by 24
- 2014Amortized tildeO(|V|)-Delay Algorithm for Listing Chordless Cycles in Undirected Graphscited by 5
Built on by
Citing papers per year: 2025: 2.
2 papers.