MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
arXiv:2007.11202
Abstract
Graph Neural Networks (GNNs) have recently caught great attention and achieved significant progress in graph-level applications. In this paper, we propose a framework for graph neural networks with multiresolution Haar-like wavelets, or MathNet, with interrelated convolution and pooling strategies. The underlying method takes graphs in different structures as input and assembles consistent graph representations for readout layers, which then accomplishes label prediction. To achieve this, the multiresolution graph representations are first constructed and fed into graph convolutional layers for processing. The hierarchical graph pooling layers are then involved to downsample graph resolution while simultaneously remove redundancy within graph signals. The whole workflow could be formed with a multi-level graph analysis, which not only helps embed the intrinsic topological information of each graph into the GNN, but also supports fast computation of forward and adjoint graph transforms. We show by extensive experiments that the proposed framework obtains notable accuracy gains on graph classification and regression tasks with performance stability. The proposed MathNet outperforms various existing GNN models, especially on big data sets.
arXiv comment32 pages, 6 figures, 6 tables
References in corpus (19)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Improving neural networks by preventing co-adaptation of feature detectors
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Geometric deep learning: going beyond Euclidean data
- Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
- Graph Neural Networks: A Review of Methods and Applications
- Fast Graph Representation Learning with PyTorch Geometric
- Pitfalls of Graph Neural Network Evaluation
- Massively Multitask Networks for Drug Discovery
- Benchmarking Graph Neural Networks
- Towards Sparse Hierarchical Graph Classifiers
- Subgraph Matching Kernels for Attributed Graphs
- Graph Wavelet Neural Network
- Learning Physical Graph Representations from Visual Scenes
- Path Integral Based Convolution and Pooling for Graph Neural Networks
- PAN: Path Integral Based Convolution for Deep Graph Neural Networks
- Walk-Steered Convolution for Graph Classification
- Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling