Mutual Information Maximization in Graph Neural Networks
| Autor: | Rui Bu, Mingchao Sun, Pengqian Yu, Xinhan Di |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Theoretical computer science Artificial neural network Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Machine Learning (stat.ML) 02 engineering and technology Maximization Mutual information 010501 environmental sciences 01 natural sciences Graph Machine Learning (cs.LG) Graph Edge Statistics - Machine Learning 020204 information systems 0202 electrical engineering electronic engineering information engineering Task analysis Symmetric matrix Feature learning 0105 earth and related environmental sciences |
| Zdroj: | IJCNN |
| Popis: | A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between nodes is inevitably lost in the scheme during learning. In order to reduce the loss, we extend the GNNs frameworks by exploring the aggregation and iteration scheme in the methodology of mutual information. We propose a new approach of enlarging the normal neighborhood in the aggregation of GNNs, which aims at maximizing mutual information. Based on a series of experiments conducted on several benchmark datasets, we show that the proposed approach improves the state-of-the-art performance for four types of graph tasks, including supervised and semi-supervised graph classification, graph link prediction and graph edge generation and classification. Accepted for presentation at IJCNN 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|