Xuemeng Song
    Assistant Professor
    Department of Computer Science and Technology
    Shandong University
    Address: Shandong University, Jimo, Tsingtao, China, 266237
    Email: sxmustc at gmail dot com
News Biography Publications Rearch
Opening for master students: I am recruiting self-motivated master students to collaborate on research domains such as information retrieval and social media analysis. Students with Bachelor's degrees in CS or other related areas (e.g, Mathematics, Physics, EE, etc.) are all welcome. (Enrollment of 2017 Sep).
Xuemeng Song is an Assistant Professor in Shandong University. She got her PhD degree from National University of Singapore and her Bacherlor degree from Universitiy of Science and Technology of China in 2016 and 2012, respectively. Her research interests are information retrieval and social media analysis. She has published several papers in the top venues, such as SIGIR, MM, IJCAI, AAAI, TOIS and TNNLS. In addition, she has served as reviewers for many top conferences and journals, such as TKDD, TMM, ICMR, and MMM.
  1. Shuhan Qi, Xuan Wang, Xi Zhang, Xuemeng Song, Zoe L. Jiang. 2018. Scalable graph based non-negative multi-view embedding for image ranking. Neurocomputing 274: 29-36. Pdf
  2. Jingyuan Chen, Xiangnan He, Xuemeng Song, Hanwang Zhang, Liqiang Nie, Tat-Seng Chua. 2018. Venue Prediction for Social Images by Exploiting Rich Temporal Patterns in LBSNs. Proc. of the ACM International Conference on MultiMedia Modeling (MMM'18), Bangkok, Thailand. Pdf
  3. Xuemeng Song, Fuli Feng, Jinhuan Liu, Zekun Li, Liqiang Nie, Jun Ma. 2017. NeuroStylist: Neural Compatibility Modeling for Clothing Matching. Proc. of the ACM International Conference on Multimedia (MM'17), Mountain View, CA USA. Pdf
  4. Xiang Wang, Liqiang Nie, Xuemeng Song, Dongxiang Zhang, and Tat-Seng Chua. 2017. Unifying virtual and physical worlds: Learning toward local and global consistency. ACM Transactions on Information Systems (TOIS). Pdf
  5. Liqiang Nie, Luming Zhang, Lei Meng, Xuemeng Song, Xiaojun Chang, Xuelong Li. 2017. Modeling Disease Progression via Multisource Multitask Learners: A Case Study With Alzheimer's Disease. IEEE Transactions on Neural Network Learning System (TNNLS). Pdf
  6. Jingyuan Chen, Xuemeng Song, Liqiang Nie, Xiang Wang, Hanwang Zhang, Tat-Seng Chua. 2016. Micro Tells Macro: Predicting the Popularity of Micro-Videos via a Transductive Model Proc. of the 24th ACM International Conference on Multimedia (MM'16), Amsterdam, Netherlands. Pdf
  7. Liqiang Nie, Xuemeng Song, Tat-Seng Chua. 2016. Learning from Multiple Social Networks. Synthesis Lectures on Information Concepts, Retrieval, and Services. Morgan & Claypool Publishers. Pdf
  8. Xuemeng Song, Zhao-Yan Ming, Liqiang Nie, Yi-Liang Zhao, and Tat-Seng Chua. 2016. Volunteerism Tendency Prediction via Harvesting Multiple Social Networks. ACM Transactions on Information Systems (TOIS). Pdf
  9. Yongpo Jia, Xuemeng Song, Jingbo Zhou, Li Liu, Liqiang Nie, and David S. Rosenblum. 2016. Fusing Social Networks with Deep Learning for Volunteerism Tendency Prediction. In Proc. of the 30th AAAI Conference on Artificial Intelligence (AAAI'16), Phoenix, Arizona USA. Pdf
  10. Xuemeng Song, Liqiang Nie, Luming Zhang, Maofu Liu, and Tat-Seng Chua. 2015. Interest Inference via Structure-Constrained Multi-Source Multi-Task Learning. In Proc. of the 24th International Joint Conference on Artificial Intelligence (IJCAI'15), Buenos Aires, Argentina. Pdf
  11. Xuemeng Song, Liqiang Nie, Luming Zhang, Mohammad Akbari, and Tat-Seng Chua. 2015. Multiple Social Network Learning and Its Application in Volunteerism Tendency Prediction. In Proc. of the 38th international ACM SIGIR conference on Research and development in information retrieval (SIGIR'15), Santiago, Chile. Pdf
  12. Xuemeng Song. 2014. Enrichment of user profiles across multiple online social networks for volunteerism matching for social enterprise. In Proc. of the 37th international ACM SIGIR conference on Research and development in information retrieval (SIGIR'14), Goad Coast, Austrilia. Pdf

Fashion Analysis towards Clothing Matching

According to the Goldman Sachs, the 2016 online retail market of China for fashion products, including apparel, footwear, and accessories, has reached 187.5 billion US dollars, which demonstrates people’s great demand for clothing. In fact, apart from physiological needs, people also have esteem needs of clothes as dressing properly is of importance in daily life. As each outfit usually involves multiple complementary items (e.g., tops, bottoms, and shoes), the key to a proper outfit lies in the harmonious clothing matching to a great extent. However, not everyone is a naturalborn fashion stylist, which makes choosing the matching clothes a tedious and even annoying daily routine. It thus deserves our attention to develop an effective clothing matching scheme to help people figure out the suitable match for a given item and make a harmonious outfit.

User Profiling across Multiple Social Networks

User profiling, which aims to infer users' unobservable information based on observable information such as individual's behavior or utterances, is the basis for many applications, such as personalized recommendation, and expert finding. Traditional user profiling conducted with traditional medium, such as document records, is always hindered by the limited data sources. Recent years, the proliferation of social media has opened new opportunities for user profiling. Moreover, as different social networks provide different services, increasing number of people are involved in multiple social networks. Different aspects can be revealed by different social networks. Therefore, to comprehensively learn users' profiles, it is time to shift from a single social network to multiple social networks.

Privacy Preserving in Social Media

The boom of social networks has given rise to a large volume of user-generated contents (UGCs), most of which are freely and publicly available. The potential of using the rich set of UGCs to study people's personal attributes and personalized applications has been widely validated. Despite its value, UGCs can also place users at high privacy risks, which thus far remains largely untapped. Privacy is defined as the individual's ability to control what information is disclosed, to whom, when and under what circumstances. As people and information both play significant roles, privacy has been elaborated as a boundary regulation process, where individuals regulate interaction with others by altering the openness degree of themselves to others. Therefore, we aim to reduce users' privacy risks on social networks by answering the question of Who Can See What.