Journal article
GANE: A Generative Adversarial Network Embedding
IEEE Transactions on Neural Networks and Learning Systems, Vol.31(7), pp.2325-2335
2020
Abstract
Network embedding is capable of providing low-dimensional feature representations for various machine learning applications. Current work focuses on: 1) designing the embedding as an unsupervised learning task to explicitly preserve the structural connectivity in the network or 2) generating the embedding as a by-product during the supervised learning of a specific discriminative task in a deep neural network. In this paper, we aim to take advantage of these two lines of research in the view of multi-output learning. That is, we propose a generative adversarial network embedding (GANE) model to adapt the generative adversarial framework to achieve the network embedding learning during the specific machine learning tasks. GANE has a generator to generate link edges, and a discriminator to distinguish the generated link edges from real connections (edges) in the network. Wasserstein-1 distance is adopted to train the generator to gain better stability. GANE is further extended by utilizing the pairwise connectivity of vertices to preserve the structural information in the original network. Experiments with real-world network data sets demonstrate that our models constantly outperform state-of-the-art solutions with significant improvements for the tasks of link prediction, clustering, and network alignment.
Details
- Title
- GANE: A Generative Adversarial Network Embedding
- Authors
- Huiting Hong (Author) - Beijing Institute of Technology, ChinaXin Li (Author) - Beijing Institute of Technology, ChinaMingzhong Wang (Author) - University of the Sunshine Coast
- Publication details
- IEEE Transactions on Neural Networks and Learning Systems, Vol.31(7), pp.2325-2335
- Publisher
- Institute of Electrical and Electronics Engineers
- Date published
- 2020
- DOI
- 10.1109/TNNLS.2019.2921841
- ISSN
- 2162-237X; 2162-237X
- Organisation Unit
- University of the Sunshine Coast, Queensland; USC Business School - Legacy; School of Science, Technology and Engineering
- Language
- English
- Record Identifier
- 99451419202621
- Output Type
- Journal article
Metrics
65 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- International collaboration
- Web Of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Hardware & Architecture
- Computer Science, Theory & Methods
- Engineering, Electrical & Electronic