On Accelerating Multi-Layered Heterogeneous Network Embedding Learning

Hong-Han Shuai, Cheng Ming Tsai, Yun Jui Hsu, Ta Che Hsiao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the rapid growth of online social networks and IoT networks, mining valuable knowledge from the graph data become important. Meanwhile, as machine learning algorithms show their powers in prediction, different machine learning algorithms are proposed for different applications, e.g., personal recommendation, price prediction, communication anomaly detection. However, it is challenging to extract network features from graph data as the inputs for machine learning algorithms. One of the promising approaches is to use graph embedding approach, which extracts the valuable information of networks from each node into low dimensional vectors. However, the graph embedding approaches on a large-scale network require tremendous training time. Therefore, in this paper, we propose NOde Differentiation for Graph Embedding (NODGE) to prioritize the nodes, while high priority nodes are allocated with more resources to train their representations. We also theoretically analyze the proposed NODGE. Experimental results show that the proposed method reduces the training time of state-of-the-art method by at least 30.7%.

Original languageEnglish
Title of host publication2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538647271
DOIs
StatePublished - 1 Jan 2018
Event2018 IEEE Global Communications Conference, GLOBECOM 2018 - Abu Dhabi, United Arab Emirates
Duration: 9 Dec 201813 Dec 2018

Publication series

Name2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings

Conference

Conference2018 IEEE Global Communications Conference, GLOBECOM 2018
CountryUnited Arab Emirates
CityAbu Dhabi
Period9/12/1813/12/18

Keywords

  • Heterogeneous information network
  • acceleration
  • graph embedding

Fingerprint Dive into the research topics of 'On Accelerating Multi-Layered Heterogeneous Network Embedding Learning'. Together they form a unique fingerprint.

Cite this