SOOP: Efficient Distributed Graph Computation Supporting Second-Order Random Walks

doi:10.1007/s11390-021-1234-y

	SOOP: Efficient Distributed Graph Computation Supporting Second-Order Random Walks
	Niu, Songjie 1,2; Zhou, Dongyan 3
刊名	JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
	2021-10-01
卷号	36 期号:5 页码:985-1001
关键词	second-order random walk (SOW) Node2Vec second-order PageRank distributed graph computation SOOP (second-order random walks with on-demand probability computation)
ISSN号	1000-9000
DOI	10.1007/s11390-021-1234-y
英文摘要	The second-order random walk has recently been shown to effectively improve the accuracy in graph analysis tasks. Existing work mainly focuses on centralized second-order random walk (SOW) algorithms. SOW algorithms rely on edge-to-edge transition probabilities to generate next random steps. However, it is prohibitively costly to store all the probabilities for large-scale graphs, and restricting the number of probabilities to consider can negatively impact the accuracy of graph analysis tasks. In this paper, we propose and study an alternative approach, SOOP (second-order random walks with on-demand probability computation), that avoids the space overhead by computing the edge-to-edge transition probabilities on demand during the random walk. However, the same probabilities may be computed multiple times when the same edge appears multiple times in SOW, incurring extra cost for redundant computation and communication. We propose two optimization techniques that reduce the complexity of computing edge-to-edge transition probabilities to generate next random steps, and reduce the cost of communicating out-neighbors for the probability computation, respectively. Our experiments on real-world and synthetic graphs show that SOOP achieves orders of magnitude better performance than baseline precompute solutions, and it can efficiently computes SOW algorithms on billion-scale graphs.
WOS研究方向	Computer Science
语种	英语
出版者	SCIENCE PRESS
WOS记录号	WOS:000712575700003
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/16926]
专题	中国科学院计算技术研究所
通讯作者	Niu, Songjie
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Bytedance Technol, Beijing 100086, Peoples R China
推荐引用方式 GB/T 7714	Niu, Songjie,Zhou, Dongyan. SOOP: Efficient Distributed Graph Computation Supporting Second-Order Random Walks[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2021,36(5):985-1001.
APA	Niu, Songjie,&Zhou, Dongyan.(2021).SOOP: Efficient Distributed Graph Computation Supporting Second-Order Random Walks.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,36(5),985-1001.
MLA	Niu, Songjie,et al."SOOP: Efficient Distributed Graph Computation Supporting Second-Order Random Walks".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 36.5(2021):985-1001.