Binarized Graph Neural Network
Preprint
Abstract
Recently, there have been some breakthroughs in graph analysis by applying the graph neural networks (GNNs) following a neighborhood aggregation scheme, which demonstrate outstanding performance in many tasks. However, we observe that the parameters of the network and the embedding of nodes are represented in real-valued matrices in existing GNN-based graph embedding approaches which may limit the efficiency and scalability of these models. It is well-known that binary vector is usually much more space and time efficient than the real-valued vector. This motivates us to develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters following the GNN-based paradigm. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches to binarize the model parameters and learn the compact embedding. Extensive experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space while matching the state-of-the-art performance.Keywords
All Related Versions
- Version 1, 2020-04-19, ArXiv
- Published version: World Wide Web, 24 (3), 825.
This publication has 8 references indexed in Scilit:
- Binarized attributed network embedding2018
- High-order Proximity Preserving Information Network Hashing2018
- Discrete Network Embedding2018
- A Survey on Network EmbeddingIEEE Transactions on Knowledge and Data Engineering, 2018
- GPH: Similarity Search in Hamming Space2018
- A Survey on Learning to HashIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Deep Supervised Hashing for Fast Image Retrieval2016
- Supervised Discrete Hashing2015