STWalk: Learning Trajectory Representations in Temporal Graphs

被引:19
作者
Pandhre, Supriya [1 ]
Mittal, Himangi [2 ]
Gupta, Manish [3 ]
Balasubramanian, Vineeth N. [1 ]
机构
[1] Indian Inst Technol Hyderabad, Hyderabad, India
[2] Jaypee Inst Informat Technol, Noida, India
[3] Microsoft, Hyderabad, India
来源
PROCEEDINGS OF THE ACM INDIA JOINT INTERNATIONAL CONFERENCE ON DATA SCIENCE AND MANAGEMENT OF DATA (CODS-COMAD'18) | 2018年
关键词
Representation Learning; Deep Learning; Temporal Graph Analysis;
D O I
10.1145/3152494.3152512
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Analyzing the temporal behavior of nodes in time-varying graphs is useful for many applications such as targeted advertising, community evolution and outlier detection. In this paper, we present a novel approach, STWalk, for learning trajectory representations of nodes in temporal graphs. The proposed framework makes use of structural properties of graphs at current and previous time-steps to learn effective node trajectory representations. STWalk performs random walks on a graph at a given time step (called space-walk) as well as on graphs from past time-steps (called time-walk) to capture the spatio-temporal behavior of nodes. We propose two variants of STWalk to learn trajectory representations. In one algorithm, we perform space-walk and time-walk as part of a single step. In the other variant, we perform space-walk and time-walk separately and combine the learned representations to get the final trajectory embedding. Extensive experiments on three real-world temporal graph datasets validate the effectiveness of the learned representations when compared to three baseline methods. We also show the goodness of the learned trajectory embeddings for change point detection, as well as demonstrate that arithmetic operations on these trajectory representations yield interesting and interpretable results.
引用
收藏
页码:210 / 219
页数:10
相关论文
共 25 条
[1]  
Aggarwal C.C., 2011, SDM, P355
[2]   Evolutionary Network Analysis: A Survey [J].
Aggarwal, Charu ;
Subbian, Karthik .
ACM COMPUTING SURVEYS, 2014, 47 (01)
[3]   Graph based anomaly detection and description: a survey [J].
Akoglu, Leman ;
Tong, Hanghang ;
Koutra, Danai .
DATA MINING AND KNOWLEDGE DISCOVERY, 2015, 29 (03) :626-688
[4]  
[Anonymous], 2012, P 5 INT C WEB SEARCH, DOI [10.1145/2124295.2124309, DOI 10.1145/2124295.2124309]
[5]  
[Anonymous], 2015, KERAS
[6]  
[Anonymous], 2005, ACM SIGKDD EXPLOR NE
[7]  
[Anonymous], 2008, Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining-KDD 08, page
[8]  
Cao S., 2015, P 24 ACM INT C INF K, P891, DOI DOI 10.1145/2806416.2806512
[9]  
Cao SS, 2016, AAAI CONF ARTIF INTE, P1145
[10]   Heterogeneous Network Embedding via Deep Architectures [J].
Chang, Shiyu ;
Han, Wei ;
Tang, Jiliang ;
Qi, Guo-Jun ;
Aggarwal, Charu C. ;
Huang, Thomas S. .
KDD'15: PROCEEDINGS OF THE 21ST ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2015, :119-128