Graph Property Prediction on Open Graph Benchmark: A Winning Solution by Graph Neural Architecture Search
Not on the map. Why?
Abstract (arXiv)
Aiming at two molecular graph datasets and one protein association subgraph dataset in OGB graph classification task, we design a graph neural network framework for graph classification task by introducing PAS(Pooling Architecture Search). At the same time, we improve it based on the GNN topology design method F2GNN to further design the feature selection and fusion strategies, so as to further improve the performance of the model in the graph property prediction task while overcoming the over smoothing problem of deep GNN training. Finally, a performance breakthrough is achieved on these three datasets, which is significantly better than other methods with fixed aggregate function. It is proved that the NAS method has high generalization ability for multiple tasks and the advantage of our method in processing graph property prediction tasks.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 30 of its 38 references that are in the map. First posted on arXiv 13 Jul 2022.
Builds on
30 of 38 references.
References · 30
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 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
- 2018DARTS: Differentiable Architecture Searchcited by 1,798
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
- 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
- 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
- 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
18 more
- 2018SNAS: Stochastic Neural Architecture Searchcited by 289
- 2015A Review of Relational Machine Learning for Knowledge Graphscited by 265
- 2020DeeperGCN: All You Need to Train Deeper GCNscited by 250
- 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
- 2022Representing Long-Range Context for Graph Neural Networks with Global Attentioncited by 195
- 2021Nested Graph Neural Networkscited by 137
- 2017CondenseNet: An Efficient DenseNet using Learned Group Convolutionscited by 122
- 2020Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classificationcited by 86
- 2019SGAS: Sequential Greedy Architecture Searchcited by 69
- 2021Understanding Pooling in Graph Neural Networkscited by 69
- 2021Search to aggregate neighborhood for graph neural networkcited by 48
- 2019GraphNAS: Graph Neural Architecture Search with Reinforcement Learningcited by 41
- 2021Pooling Architecture Search for Graph Classificationcited by 36
- 2020Simplifying Architecture Search for Graph Neural Networkcited by 28
- 2021Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspectivecited by 19
- 2020Breaking the Expressive Bottlenecks of Graph Neural Networkscited by 6
- 2021GraphPAS: Parallel Architecture Search for Graph Neural Networkscited by 5
- 2022Graph Neural Networks for Double-Strand DNA Breaks Predictioncited by 1
Built on by
Citing papers per year: 2023: 2.
2 papers.