A Self-Attention Network Based Node Embedding Model
Abstract
Despite several signs of progress have been made recently, limited research has been conducted for an inductive setting where embeddings are required for newly unseen nodes -- a setting encountered commonly in practical applications of deep learning for graph networks. This significantly affects the performances of downstream tasks such as node classification, link prediction or community extraction. To this end, we propose SANNE -- a novel unsupervised embedding model -- whose central idea is to employ a transformer self-attention network to iteratively aggregate vector representations of nodes in random walks. Our SANNE aims to produce plausible embeddings not only for present nodes, but also for newly unseen nodes. Experimental results show that the proposed SANNE obtains state-of-the-art results for the node classification task on well-known benchmark datasets.
Cite
Text
Nguyen et al. "A Self-Attention Network Based Node Embedding Model." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020. doi:10.1007/978-3-030-67664-3_22Markdown
[Nguyen et al. "A Self-Attention Network Based Node Embedding Model." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020.](https://mlanthology.org/ecmlpkdd/2020/nguyen2020ecmlpkdd-selfattention/) doi:10.1007/978-3-030-67664-3_22BibTeX
@inproceedings{nguyen2020ecmlpkdd-selfattention,
title = {{A Self-Attention Network Based Node Embedding Model}},
author = {Nguyen, Dai Quoc and Nguyen, Tu Dinh and Phung, Dinh},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2020},
pages = {364-377},
doi = {10.1007/978-3-030-67664-3_22},
url = {https://mlanthology.org/ecmlpkdd/2020/nguyen2020ecmlpkdd-selfattention/}
}