Publication: DGSD: Distributed graph representation via graph statistical properties
2
Issued Date
2021-06-01
Resource Type
ISSN
0167739X
Other identifier(s)
2-s2.0-85101572791
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
Future Generation Computer Systems. Vol.119, (2021), 166-175
Suggested Citation
Anwar Said, Saeed Ul Hassan, Suppawong Tuarob, Raheel Nawaz, Mudassir Shabbir DGSD: Distributed graph representation via graph statistical properties. Future Generation Computer Systems. Vol.119, (2021), 166-175. doi:10.1016/j.future.2021.02.005 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/76648
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
DGSD: Distributed graph representation via graph statistical properties
Other Contributor(s)
Abstract
Graph encoding methods have been proven exceptionally useful in many classification tasks — from molecule toxicity prediction to social network recommendations. However, most of the existing methods are designed to work in a centralized environment that requires the whole graph to be kept in memory. Moreover, scaling them on very large networks remains a challenge. In this work, we propose a distributed and permutation invariant graph embedding method denoted as Distributed Graph Statistical Distance (DGSD) that extracts graph representation on independently distributed machines. DGSD finds nodes’ local proximity by considering only nodes’ degree, common neighbors and direct connectivity that allows it to run in the distributed environment. On the other hand, the linear space complexity of DGSD makes it suitable for processing large graphs. We show the scalability of DGSD on sufficiently large random and real-world networks and evaluate its performance on various bioinformatics and social networks with the implementation in a distributed computing environment.