A Simple Meta-path-free Framework for Heterogeneous Network Embedding
Authors:
Open Access
- 17 October 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2600-2609
Abstract
Network embedding has recently attracted attention a lot since networks are widely used in various data mining applications. Attempting to break the limitations of pre-set meta-paths and non-global node learning in existing models, we propose a simple but effective framework for heterogeneous network embedding learning by encoding the original multi-type nodes and relations directly in a self-supervised way. To be more specific, we first learn the relation-based embeddings for global nodes from the neighbor properties under each relation type and exploit an attentive fusion module to combine them. Then we design a multi-hop contrast to optimize the regional structure information by utilizing the strong correlation between nodes and their neighbor-graphs, where we take multiple relationships into consideration by multi-hop message passing instead of pre-set meta-paths. Finally, we evaluate our proposed method on various downstream tasks such as node clustering, node classification, and link prediction between two types of nodes. The experimental results show that our proposed approach significantly outperforms state-of-the-art baselines on these tasks.Keywords
Funding Information
- China Scholarship Council (201706030151)
This publication has 12 references indexed in Scilit:
- HDMI: High-order Deep Multiplex Infomax2021
- Graph Representation Learning via Graphical Mutual Information Maximization2020
- Unsupervised Attributed Multiplex Network EmbeddingProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Adversarial Learning on Heterogeneous Information Networks2019
- Heterogeneous Graph Attention Network2019
- Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks2018
- metapath2vec2017
- node2vec2016
- Unsupervised Visual Representation Learning by Context Prediction2015
- DeepWalk2014