Temporal Network Representation Learning via Historical Neighborhoods Aggregation
| Autor: | Zhifeng Bao, Shixun Huang, J. Shane Culpepper, Guoliang Li, Yanghao Zhou |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Theoretical computer science business.industry Computer science Deep learning Machine Learning (stat.ML) 02 engineering and technology Random walk Visualization Machine Learning (cs.LG) Evolving networks Data visualization Statistics - Machine Learning 020204 information systems Node (computer science) 0202 electrical engineering electronic engineering information engineering Task analysis Feature (machine learning) 020201 artificial intelligence & image processing The Internet Artificial intelligence business |
| Zdroj: | ICDE |
| DOI: | 10.48550/arxiv.2003.13212 |
| Popis: | Network embedding is an effective method to learn low-dimensional representations of nodes, which can be applied to various real-life applications such as visualization, node classification, and link prediction. Although significant progress has been made on this problem in recent years, several important challenges remain, such as how to properly capture temporal information in evolving networks. In practice, most networks are continually evolving. Some networks only add new edges or nodes such as authorship networks, while others support removal of nodes or edges such as internet data routing. If patterns exist in the changes of the network structure, we can better understand the relationships between nodes and the evolution of the network, which can be further leveraged to learn node representations with more meaningful information. In this paper, we propose the Embedding via Historical Neighborhoods Aggregation (EHNA) algorithm. More specifically, we first propose a temporal random walk that can identify relevant nodes in historical neighborhoods which have impact on edge formations. Then we apply a deep learning model which uses a custom attention mechanism to induce node embeddings that directly capture temporal information in the underlying feature representation. We perform extensive experiments on a range of real-world datasets, and the results demonstrate the effectiveness of our new approach in the network reconstruction task and the link prediction task. Comment: 28 Pages, published in 2020 IEEE International Conference on Data Engineering (ICDE 2020) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|