TY - GEN
T1 - HetespaceyWalk
T2 - 28th ACM International Conference on Information and Knowledge Management, CIKM 2019
AU - He, Yu
AU - Song, Yangqiu
AU - Li, Jianxin
AU - Ji, Cheng
AU - Peng, Jian
AU - Peng, Hao
N1 - Funding Information:
This work is supported by the China NSFC program (No.61872022, 61421003), SKLSDE-2018ZX16, and the Early Career Scheme (ECS, No.26206717) from Research Grants Council in Hong Kong. For any correspondence, please refer to Jianxin Li.
Funding Information:
This work is supported by the China NSFC program (No.61872022, 61421003) , SKLSDE-2018ZX16, and the Early Career Scheme (ECS, No.26206717) from Research Grants Council in Hong Kong. For any correspondence, please refer to Jianxin Li.
Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/11/3
Y1 - 2019/11/3
N2 - Heterogeneous information network (HIN) embedding has gained increasing interests recently. However, the current way of random-walk based HIN embedding methods have paid few attention to the higher-order Markov chain nature of meta-path guided random walks, especially to the stationarity issue. In this paper, we systematically formalize the meta-path guided random walk as a higher-order Markov chain process, and present a heterogeneous personalized spacey random walk to efficiently and effectively attain the expected stationary distribution among nodes. Then we propose a generalized scalable framework to leverage the heterogeneous personalized spacey random walk to learn embeddings for multiple types of nodes in an HIN guided by a meta-path, a meta-graph, and a meta-schema respectively. We conduct extensive experiments in several heterogeneous networks and demonstrate that our methods substantially outperform the existing state-of-the-art network embedding algorithms.
AB - Heterogeneous information network (HIN) embedding has gained increasing interests recently. However, the current way of random-walk based HIN embedding methods have paid few attention to the higher-order Markov chain nature of meta-path guided random walks, especially to the stationarity issue. In this paper, we systematically formalize the meta-path guided random walk as a higher-order Markov chain process, and present a heterogeneous personalized spacey random walk to efficiently and effectively attain the expected stationary distribution among nodes. Then we propose a generalized scalable framework to leverage the heterogeneous personalized spacey random walk to learn embeddings for multiple types of nodes in an HIN guided by a meta-path, a meta-graph, and a meta-schema respectively. We conduct extensive experiments in several heterogeneous networks and demonstrate that our methods substantially outperform the existing state-of-the-art network embedding algorithms.
KW - Heterogeneous networks
KW - Network embedding
KW - Random walk
UR - http://www.scopus.com/inward/record.url?scp=85075430689&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075430689&partnerID=8YFLogxK
U2 - 10.1145/3357384.3358061
DO - 10.1145/3357384.3358061
M3 - Conference contribution
AN - SCOPUS:85075430689
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 639
EP - 648
BT - CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
Y2 - 3 November 2019 through 7 November 2019
ER -