Xinjiang Lu

Xinjiang Lu

Auto-generated profile, based on publicly available information

Xinjiang Lu

Frontier Research Department, Baidu Inc., Beijing, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 January 2016 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
YFYanjie Fu
Yanjie Fu
HXHui Xiong
Hui Xiong
XLXinjiang Lu
Xinjiang Lu
JYJin Yang
Jin Yang
CCCan Chen
Can Chen
The rapid adoption of mobile messaging Apps has enabled us to collect massive amount of encrypted Internet traffic of mobile messaging. The classification of this traffic into different types of in-App service usages can help for intelligent network management, such as managing network bandwidth budget and providing quality of services. Traditional approaches for classification of Internet traffic rely on packet inspection, such as parsing HTTP headers. However, messaging Apps are increasingly using secure protocols, such as HTTPS and SSL, to transmit data. This imposes significant challenges on the performances of service usage classification by packet inspection. To this end, in this paper, we investigate how to exploit encrypted Internet traffic for classifying in-App usages. Specifically, we develop a system, named CUMMA, for classifying service usages of mobile messaging Apps by jointly modeling user behavioral patterns, network traffic characteristics, and temporal dependencies. Along this line, we first segment Internet traffic from traffic-flows into sessions with a number of dialogs in a hierarchical way. Also, we extract the discriminative features of traffic data from two perspectives: (i) packet length and (ii) time delay. Next, we learn a service usage predictor to classify these segmented dialogs into single-type usages or outliers. In addition, we design a clustering Hidden Markov Model (HMM) based method to detect mixed dialogs from outliers and decompose mixed dialogs into sub-dialogs of single-type usage. Indeed, CUMMA enables mobile analysts to identify service usages and analyze end-user in-App behaviors even for encrypted Internet traffic. Finally, the extensive experiments on real-world messaging data demonstrate the effectiveness and efficiency of the proposed method for service usage classification.

10 April 2020 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
HLHao Liu
Hao Liu
YTYongxin Tong
Yongxin Tong
JHJindong Han
Jindong Han
PZPanpan Zhang
Panpan Zhang
XLXinjiang Lu
Xinjiang Lu
HXHui Xiong
Hui Xiong
Transportation recommendation is one important map service in navigation applications. Previous transportation recommendation solutions fail to deliver satisfactory user experience because their recommendations only consider routes in one transportation mode (uni-modal, e.g., taxi, bus, cycle) and largely overlook situational context. In this work, we propose Hydra, a multi-task deep learning based recommendation system that offers multi-modal transportation planning and is adaptive to various situational context (e.g., nearby point-of-interest~(POI) distribution and weather). We design a novel two-level framework that integrates uni-modal and multi-modal~(e.g., taxi-bus, bus-cycle) routes as well as heterogeneous urban data for intelligent multi-modal transportation recommendation. In addition to urban context features constructed from multi-source urban data, we learn the latent representations of users, origin-destination~(OD) pairs and transportation modes based on user implicit feedbacks. Moreover, we propose two models to recommend the proper route among various uni-modal and multi-modal transportation routes: (1) a light-weight gradient boosting decision tree (GBDT) based recommendation model; and (2) a multi-task wide and deep learning (MTWDL) based recommendation model. We also optimize the framework to support real-time, large-scale route query and recommendation. We deploy Hydra on Baidu Maps, one of the world's largest map services. The GBDT based model and MTWDL based variants achieve 82.8% and 96.6% relative improvement of user click ratio, respectively.

13 August 2017
Verified
Conference Paper
Open access
YLYanchi Liu
Yanchi Liu
CLChuanren Liu
Chuanren Liu
XLXinjiang Lu
Xinjiang Lu
MTMingfei Teng
Mingfei Teng
HZHengshu Zhu
Hengshu Zhu
HXHui Xiong
Hui Xiong
Point-of-Interest (POI) demand modeling in urban regions is critical for many applications such as business site selection and real estate investment. While some efforts have been made for the demand analysis of some specific POI categories, such as restaurants, it lacks systematic means to support POI demand modeling. To this end, in this paper, we develop a systematic POI demand modeling framework, named Region POI Demand Identification (RPDI), to model POI demands by exploiting the daily needs of people identified from their large-scale mobility data. Specifically, we first partition the urban space into spatially differentiated neighborhood regions formed by many small local communities. Then, the daily activity patterns of people traveling in the city will be extracted from human mobility data. Since the trip activities, even aggregated, are sparse and insufficient to directly identify the POI demands, especially for underdeveloped regions, we develop a latent factor model that integrates human mobility data, POI profiles, and demographic data to robustly model the POI demand of urban regions in a holistic way. In this model, POI preferences and supplies are used together with demographic features to estimate the POI demands simultaneously for all the urban regions interconnected in the city. Moreover, we also design efficient algorithms to optimize the latent model for large-scale data. Finally, experimental results on real-world data in New York City (NYC) show that our method is effective for identifying POI demands for different regions.

1 June 2014 in Journal of Network and Computer Applications
Verified
Journal Article
Open access
XLXinjiang Lu
Xinjiang Lu
ZYZhiwen Yu
Zhiwen Yu
BGBin Guo
Bin Guo
XZXingshe Zhou
Xingshe Zhou
Internet of Things (IoT) invasions a future in which digital and physical entities (e.g., mobile devices, wearable devices) can be linked, by means of appropriate information and communication technologies, to enable a whole new class of applications and services. In this paper, we study the dissemination of content over a mobile social network, which has become an attractive proxy for investigating human behaviors due to the rapid development of mobile phones. One of the most interesting and challenging problems about content dissemination is that how much attention of a specific post from a user can ultimately gain? Hence, in other words, can we forecast the crowds׳ concern in the mobile social networking environment, and how? We try to tackle this issue by exploring approaches to predict the amount of reposts any given post will obtain in Sina Weibo, a well-known mobile social networking service in China. We examine several novel implicit factors impacting the popularity of content, such as Modality, MaxMediaWeight and Activeness. Furthermore, we propose a RepostsTree based method to model the reposting process in a temporal dynamic manner. Experimental results over the collected data from Sina Weibo indicate that our method is effective on content diffusion prediction in mobile social networks

1 January 2022
Verified
Conference Paper
Open access
PDF file
MCMiao Chen
Miao Chen
XLXinjiang Lu
Xinjiang Lu
Tong XuTong Xu
Tong Xu
YLYanyan Li
Yanyan Li
ZJZhou Jingbo
Zhou Jingbo
HXHui Xiong
Hui Xiong
Miao Chen, Xinjiang Lu, Tong Xu, Yanyan Li, Zhou Jingbo, Dejing Dou, Hui Xiong. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

1 November 2015
Verified
Conference Paper
Closed access
CGChu Guan
Chu Guan
XLXinjiang Lu
Xinjiang Lu
XLXiaolin Li
Xiaolin Li
ECEnhong Chen
Enhong Chen
WZWenjun Zhou
Wenjun Zhou
HXHui Xiong
Hui Xiong
College students with financial difficulties refer to those whose families can hardly afford their high tuition in universities, and should be supported by modern funding system. Indeed, students' economic plight negatively impact their mental health, academic performance, as well as their personal and social life. While funding students in financial hardship is widely accepted, there is limited understanding and research on effectively identification of the qualifying students. Traditional approaches relying on advisers' personal assessments are inefficient, and such subjective judgements may not reflect the truth. To this end, in this paper, we explore the data mining techniques for identifying students who are qualified for financial support. Specifically, we investigate students' complex behaviors on campus from multiple perspectives, and develop a learning framework, named Dis-HARD, by jointly incorporating the heterogeneous features to predict the portfolio of stipends a given student should be awarded. Our framework formalizes the above problem as a multi-label learning problem. Along this line, we first extract discriminative features from three perspectives: (i) smartcard usage behavior, (ii) internet usage behavior and (iii) trajectory on campus. Then, we develop a linear loss function with regularization to solve this multi-label classification problem. In addition, to effectively exploit the students' similarity and label dependency, we incorporate the graph Laplacian and composite l2,1-norm into the regularization of our model, and develop are-weighted algorithm to achieve effective optimization. Finally, experiments on real-world data demonstrate that our method consistently provides better performance compared to the existing state-of-the-art methods.