PAN: Path Integral Based Convolution for Deep Graph Neural Networks
arXiv:1904.10996
Abstract
Convolution operations designed for graph-structured data usually utilize the graph Laplacian, which can be seen as message passing between the adjacent neighbors through a generic random walk. In this paper, we propose PAN, a new graph convolution framework that involves every path linking the message sender and receiver with learnable weights depending on the path length, which corresponds to the maximal entropy random walk. PAN generalizes the graph Laplacian to a new transition matrix we call \emph{maximal entropy transition} (MET) matrix derived from a path integral formalism. Most previous graph convolutional network architectures can be adapted to our framework, and many variations and derivatives based on the path integral idea can be developed. Experimental results show that the path integral based graph neural networks have great learnability and fast convergence rate, and achieve state-of-the-art performance on benchmark tasks.
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Geometric deep learning: going beyond Euclidean data
- Simplifying Graph Convolutional Networks
- Gated Graph Sequence Neural Networks
- Revisiting Semi-Supervised Learning with Graph Embeddings
- Attention-based Graph Neural Network for Semi-supervised Learning
- Localization of maximal entropy random walk
- LanczosNet: Multi-Scale Deep Graph Convolutional Networks
- Robust Spatial Filtering with Graph Convolutional Neural Networks
- Graph Wavelet Neural Network
- Maximal entropy random walk in community finding
- FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis