Attentional Multilabel Learning over Graphs: A Message Passing Approach
arXiv:1804.00293
Abstract
We address a largely open problem of multilabel classification over graphs. Unlike traditional vector input, a graph has rich variable-size substructures which are related to the labels in some ways. We believe that uncovering these relations might hold the key to classification performance and explainability. We introduce GAML (Graph Attentional Multi-Label learning), a novel graph neural network that can handle this problem effectively. GAML regards labels as auxiliary nodes and models them in conjunction with the input graph. By applying message passing and attention mechanisms to both the label nodes and the input nodes iteratively, GAML can capture the relations between the labels and the input subgraphs at various resolution scales. Moreover, our model can take advantage of explicit label dependencies. It also scales linearly with the number of labels and graph size thanks to our proposed hierarchical attention. We evaluate GAML on an extensive set of experiments with both graph-structured inputs and classical unstructured inputs. The results show that GAML significantly outperforms other competing methods. Importantly, GAML enables intuitive visualizations for better understanding of the label-substructure relations and explanation of the model behaviors.
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Spectral Networks and Locally Connected Networks on Graphs
- Training Very Deep Networks
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- Learning Convolutional Neural Networks for Graphs
- Deep Convolutional Ranking for Multilabel Image Annotation
- Modeling Relational Data with Graph Convolutional Networks
- Network Representation Learning: A Survey
- Graph Convolutional Networks for Classification with a Structured Label Space
- One Size Fits Many: Column Bundle for Multi-X Learning