RoSANE: Robust and scalable attributed network embedding for sparse networks

Hou，Chengbin1,2; He，Shan2; Tang，Ke1

2020-10-07

10.1016/j.neucom.2020.05.080

NEUROCOMPUTING   影响因子和分区

0925-2312

1872-8286

Attributed networks can better describe the real-world complex systems where the interaction or relationship between entities can be represented as networks and the auxiliary information can be represented as node attributes. Attributed Network Embedding (ANE) is attracting much attention. It utilizes network topology and node attributes to jointly learn enhanced low-dimensional node embeddings so as to facilitate various downstream inference tasks. However, the existing ANE methods cannot effectively embed attributed sparse networks which are important real-world scenarios, and/or are not scalable to large-scale networks. To tackle these challenges, we first integrate network topology and node attributes to reconstruct an enriched denser network, and then learn node embeddings upon the denser network. In above two steps, the techniques such as Ball-tree K-Nearest Neighbors and random walks based Skip-Gram model are adopted to guarantee the scalability, which is demonstrated via theoretical complexity analysis. The extensive empirical studies show the effectiveness and efficiency of the proposed method, as well as its robustness to different networks or the same network with different sparsities.

Attributed Network Embedding Ball-tree K-nearest neighbors Random walks Skip-gram model Sparse networks

SCI ; EI

英语

第一

Natural Science Foundation of China[61672478] ; Guangdong Provincial Key Laboratory[2020B121201001] ; Program for Guangdong Introducing Innovative and Entrepreneurial Teams[2017ZT07X386] ; Shenzhen Peacock Plan[KQTD2016112514355531]

Computer Science

Computer Science, Artificial Intelligence

WOS:000562543100019

ELSEVIER

20202508851862

Complex networks ; Network topology ; Forestry ; Nearest neighbor search ; Random processes

Electric Networks:703.1 ; Computer Systems and Equipment:722 ; Artificial Intelligence:723.4 ; Agricultural Equipment and Methods; Vegetation and Pest Control:821 ; Optimization Techniques:921.5 ; Probability Theory:922.1

COMPUTER SCIENCE

2-s2.0-85086571387

Scopus

1.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,China
2.School of Computer Science,University of Birmingham,Birmingham,United Kingdom

Hou，Chengbin,He，Shan,Tang，Ke. RoSANE: Robust and scalable attributed network embedding for sparse networks[J]. NEUROCOMPUTING,2020,409:231-243.

Hou，Chengbin,He，Shan,&Tang，Ke.(2020).RoSANE: Robust and scalable attributed network embedding for sparse networks.NEUROCOMPUTING,409,231-243.

Hou，Chengbin,et al."RoSANE: Robust and scalable attributed network embedding for sparse networks".NEUROCOMPUTING 409(2020):231-243.