ABSTRACT
Recent advances in network representation learning have enabled significant improvements in the link prediction task, which is at the core of many downstream applications. As an increasing amount of mobility data becoming available due to the development of location technologies, we argue that this resourceful user mobility data can be used to improve link prediction performance. In this paper, we propose a novel link prediction framework that utilizes user offline check-in behavior combined with user online social relations. We model user offline location preference via probabilistic factor model and represent user social relations using neural network embedding. Furthermore, we employ locality-sensitive hashing to project the aggregated user representation into a binary matrix, which not only preserves the data structure but also speeds up the followed convolutional network learning. By comparing with several baseline methods that solely rely on social network or mobility data, we show that our unified approach significantly improves the performance.
- Michael Backes, Mathias Humbert, Jun Pang, and Yang Zhang. 2017. walk2friends: Inferring Social Links from Mobility Profiles. In CCS . Google ScholarDigital Library
- Hongyun Cai, Vincent W Zheng, and Kevin Chen-Chuan Chang. 2017. A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications. (2017). arxiv: 1709.07604v1Google Scholar
- Shaosheng Cao, Wei Lu, and Qiongkai Xu. 2015. GraRep: Learning Graph Representations with Global Structural Information. In CIKM . Google ScholarDigital Library
- Moses Charikar. 2002. Similarity estimation techniques from rounding algorithms. In STOC . Google ScholarDigital Library
- Ye Chen, Michael Kapralov, Dmitry Pavlov, and John F Canny. 2009. Factor Modeling for Advertisement Targeting. In NIPS . Google ScholarDigital Library
- Sanjoy Dasgupta, Charles F Stevens, and Saket Navlakha. 2017. A neural algorithm for a fundamental computing problem. Science , Vol. 358, 6364 (2017), 793--796.Google Scholar
- Michel X Goemans and David P Williamson. 1995. Improved Approximation Algorithms for Maximum Cut and Satisfiability Problems Using Semidefinite Programming. J. ACM (1995). Google ScholarDigital Library
- Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable Feature Learning for Networks. In KDD . Google ScholarDigital Library
- William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Representation Learning on Graphs: Methods and Applications. IEEE Data Eng. Bull. , Vol. 40, 3 (2017), 52--74.Google Scholar
- Hsun-Ping Hsieh, Rui Yan, and Cheng-Te Li. 2015. Where You Go Reveals Who You Know: Analyzing Social Ties from Millions of Footprints. In CIKM . Google ScholarDigital Library
- Qinghao Hu, Peisong Wang, and Jian Cheng. 2018. From Hashing to CNNs: Training Binary Weight Networks via Hashing. In AAAI .Google Scholar
- Piotr Indyk and Rajeev Motwani. 1998. Approximate Nearest Neighbors: Towards Removing the Curse of Dimensionality. In STOC . Google ScholarDigital Library
- David Liben-Nowell and Jon M Kleinberg. 2003. The link prediction problem for social networks. In CIKM . Google ScholarDigital Library
- Bin Liu, Hui Xiong, Spiros Papadimitriou, Yanjie Fu, and Zijun Yao. 2015. A General Geographical Probabilistic Factor Model for Point of Interest Recommendation. TKDE (2015).Google Scholar
- Hao Ma, Chao Liu, Irwin King, and Michael R Lyu. 2011. Probabilistic factor models for web site recommendation. In SIGIR . Google ScholarDigital Library
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. DeepWalk: Online Learning of Social Representations. In KDD . Google ScholarDigital Library
- L. F. Rodrigues Ribeiro, Pedro H. P. Saverese, and Daniel R. Figueiredo. 2017. struc2vec: Learning Node Representations from Structural Identity. In KDD . Google ScholarDigital Library
- Anshumali Shrivastava and Ping Li. 2014. Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS). In NIPS . Google ScholarDigital Library
- Ryan Spring and Anshumali Shrivastava. 2017. Scalable and Sustainable Deep Learning via Randomized Hashing. In KDD . Google ScholarDigital Library
- Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. 2015. LINE: Large-scale Information Network Embedding. In WWW . Google ScholarDigital Library
- Cheng Wang, Jieren Zhou, and Bo Yang. 2017b. From Footprint to Friendship: Modeling User Followership in Mobile Social Networks From Check-in Data. In SIGIR . Google ScholarDigital Library
- Dashun Wang, Dino Pedreschi, Chaoming Song, Fosca Giannotti, and Albert-László Barabási. 2011. Human mobility, social ties, and link prediction. In KDD . Google ScholarDigital Library
- Hongjian Wang, Zhenhui Li, and Wang-Chien Lee. 2014. PGT: Measuring Mobility Relationship Using Personal, Global and Temporal Factors. In ICDM . Google ScholarDigital Library
- Pinghui Wang, Feiyang Sun, Di Wang, Jing Tao, Xiaohong Guan, and Albert Bifet. 2017a. Inferring Demographics and Social Networks of Mobile Device Users on Campus From AP-Trajectories. In WWW . Google ScholarDigital Library
Index Terms
- vec2Link: Unifying Heterogeneous Data for Social Link Prediction
Recommendations
Friendship Maintenance and Prediction in Multiple Social Networks
HT '16: Proceedings of the 27th ACM Conference on Hypertext and Social MediaDue to the proliferation of online social networks (OSNs), users find themselves participating in multiple OSNs. These users leave their activity traces as they maintain friendships and interact with other users in these OSNs. In this work, we analyze ...
Network Embedding by Resource-Allocation for Link Prediction
PRICAI 2019: Trends in Artificial IntelligenceAbstractIn network embedding, the analysis of the relationship between nodes has a great influence on the link prediction. In this paper, we re-examine the role of network topology in predicting missing links from the perspective of node embedding, and ...
NetMerger: Predicting Cross-network Links in Merged Heterogeneous Networks
WI '19 Companion: IEEE/WIC/ACM International Conference on Web Intelligence - Companion VolumePrevious work on link prediction focuses on single network settings or transferring knowledge between two networks for predicting intra-network links. However, many real-world applications involve multiple networks, and we need to predict cross-network ...
Comments