Factor Graph Neural Network
arXiv:1906.00554
Abstract
Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks. Recently, graph neural networks have been successfully applied to graph structured data such as point cloud and molecular data. These networks often only consider pairwise dependencies, as they operate on a graph structure. We generalize the graph neural network into a factor graph neural network (FGNN) in order to capture higher order dependencies. We show that FGNN is able to represent Max-Product Belief Propagation, an approximate inference algorithm on probabilistic graphical models; hence it is able to do well when Max-Product does well. Promising results on both synthetic and real datasets demonstrate the effectiveness of the proposed model.
References in corpus (9)
- Semi-Supervised Classification with Graph Convolutional Networks
- Neural Message Passing for Quantum Chemistry
- Spectral Networks and Locally Connected Networks on Graphs
- Molecular Graph Convolutions: Moving Beyond Fingerprints
- Quantum-Chemical Insights from Deep Tensor Neural Networks
- Learning Combinatorial Optimization Algorithms over Graphs
- Interaction Networks for Learning about Objects, Relations and Physics
- Gated Graph Sequence Neural Networks
- How Powerful are Graph Neural Networks?