Uplifting Message Passing Neural Network with Graph Original Information
Not on the map. Why?
Abstract (arXiv)
Message passing neural networks (MPNNs) learn the representation of graph-structured data based on graph original information, including node features and graph structures, and have shown astonishing improvement in node classification tasks. However, the expressive power of MPNNs is upper bounded by the first-order Weisfeiler-Leman test and its accuracy still has room for improvement. This work studies how to improve MPNNs' expressiveness and generalizability by fully exploiting graph original information both theoretically and empirically. It further proposes a new GNN model called INGNN (INformation-enhanced Graph Neural Network) that leverages the insights to improve node classification performance. Extensive experiments on both synthetic and real datasets demonstrate the superiority (average rank 1.78) of our INGNN compared with state-of-the-art methods.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 41 of its 48 references that are in the map. First posted on arXiv 8 Oct 2022.
Builds on
41 of 48 references.
References · 41
- 2017Attention Is All You Needcited by 60,361
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2018DARTS: Differentiable Architecture Searchcited by 1,798
- 2019Simplifying Graph Convolutional Networkscited by 1,477
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
29 more
- 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
- 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
- 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
- 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
- 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
- 2019Provably Powerful Graph Networkscited by 389
- 2018Invariant and Equivariant Graph Networkscited by 346
- 2016Learning Convolutional Neural Networks for Graphscited by 314
- 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 313
- 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
- 2020Towards Deeper Graph Neural Networkscited by 296
- 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 260
- 2020Can Graph Neural Networks Count Substructures?cited by 236
- 2020The Surprising Power of Graph Neural Networks with Random Node Initializationcited by 198
- 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
- 2020Random Features Strengthen Graph Neural Networkscited by 186
- 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
- 2019On the equivalence between graph isomorphism testing and function approximation with GNNscited by 172
- 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 155
- 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
- 2020A Survey on The Expressive Power of Graph Neural Networkscited by 111
- 2020Expressive Power of Invariant and Equivariant Graph Neural Networkscited by 100
- 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
- 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
- 2018On Weisfeiler-Leman Invariance: Subgraph Counts and Related Graph Propertiescited by 63
- 2021Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddingscited by 49
- 2021AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filtercited by 43
- 2020Expertise and Dynamics within Crowdsourced Musical Knowledge Curation: A Case Study of the Genius Platformcited by 13
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.