Cheng Wang

Cheng Wang


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
22 May 2023 in ACM Transactions on the Web
Verified
Journal Article
Open access
JGJibing Gong
Jibing Gong
YWYao Wan
Yao Wan
YLYe Liu
Ye Liu
XLXuewen Li
Xuewen Li
YZYi Zhao
Yi Zhao
JTJie Tang
Jie Tang
Massive open online courses (MOOCs), which offer open access and widespread interactive participation through the internet, are quickly becoming the preferred method for online and remote learning. Several MOOC platforms offer the service of course recommendation to users, to improve the learning experience of users. Despite the usefulness of this service, we consider that recommending courses to users directly may neglect their varying degrees of expertise. To mitigate this gap, we examine an interesting problem of concept recommendation in this paper, which can be viewed as recommending knowledge to users in a fine-grained way. We put forward a novel approach, termedHinCRec-RL, forConceptRecommendation in MOOCs, which is based onHeterogeneousInformationNetworks andReinforcementLearning. In particular, we propose to shape the problem of concept recommendation within a reinforcement learning framework to characterize the dynamic interaction between users and knowledge concepts in MOOCs. Furthermore, we propose to form the interactions among users, courses, videos, and concepts into aheterogeneous information network (HIN)to learn the semantic user representations better. We then employ an attentional graph neural network to represent the users in the HIN, based on meta-paths. Extensive experiments are conducted on a real-world dataset collected from a Chinese MOOC platform,XuetangX, to validate the efficacy of our proposed HinCRec-RL. Experimental results and analysis demonstrate that our proposed HinCRec-RL performs well when compared with several state-of-the-art models.

13 July 2021 in Electronics
Verified
Journal Article
Open access
PDF file
JGJibing Gong
Jibing Gong
CWCheng Wang
Cheng Wang
智赵智永 赵
智永 赵
XZxinghao zhang
xinghao zhang
In MOOCs, generally speaking, curriculum designing, course selection, and knowledge concept recommendation are the three major steps that systematically instruct users to learn. This paper focuses on the knowledge concept recommendation in MOOCs, which recommends related topics to users to facilitate their online study. The existing approaches only consider the historical behaviors of users, but ignore various kinds of auxiliary information, which are also critical for user embedding. In addition, traditional recommendation models only consider the immediate user response to the recommended items, and do not explicitly consider the long-term interests of users. To deal with the above issues, this paper proposes AGMKRec, a novel reinforced concept recommendation model with a heterogeneous information network. We first clarify the concept recommendation in MOOCs as a reinforcement learning problem to offer a personalized and dynamic knowledge concept label list to users. To consider more auxiliary information of users, we construct a heterogeneous information network among users, courses, and concepts, and use a meta-path-based method which can automatically identify useful meta-paths and multi-hop connections to learn a new graph structure for learning effective node representations on a graph. Comprehensive experiments and analyses on a real-world dataset collected from XuetangX show that our proposed model outperforms some state-of-the-art methods.

12 August 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JGJibing Gong
Jibing Gong
XZxinghao zhang
xinghao zhang
QLQing Li
Qing Li
CWCheng Wang
Cheng Wang
XZxinghao zhang
xinghao zhang
SWShuli Wang
Shuli Wang
To provide more accurate and stable recommendations, it is necessary to combine display information with implicit information and to dig out potential information. Existing methods only consider explicit feedback information or implicit feedback information unilaterally and ignore the potential information of explicit feedback information and implicit feedback information, which is also crucial to the accuracy of the recommendation system. However, the traditional Heterogeneous Information Networks (HIN) recommendation ignores the attribute information in the meta-path and the interaction between the user and the item and, instead, only considers the linear characteristics of the user-object often ignoring its non-linear characteristics. Aiming at the potential information acquisition problem from assorted feedback, we propose a new top-N recommendation method MFDNN for Heterogeneous Information Networks (HINs). First, we consider explicit and implicit feedback information to determine the potential preferences of users and the potential features of the product. Then, matrix factorization (MF) and a deep neural network (DNN) are fused to learn independent feature embeddings through MF and DNN, and fully considering the linear and non-linear characteristics of the user-object. MFDNN was tested on several real data sets, such as Movie-Lens, and compared with benchmark experiments. MFDNN significantly improved the hit ratio (HR) and normalized discounted cumulative gain (NDCG). Further research showed that the meta-path bias had an excellent effect on the gain of potential information mining and the fusion of explicit and implicit information in the accuracy and stability of user interest classification.

4 September 2013 in arXiv
Verified
Preprint
Open access
PDF file
CWCheng Wang
Cheng Wang
BUBhuvan Urgaonkar
Bhuvan Urgaonkar
QWQian Wang
Qian Wang
GKGeorge Kesidis
George Kesidis
ASAnand Sivasubramaniam
Anand Sivasubramaniam
We formulate optimization problems to study how data centers might modulate their power demands for cost-effective operation taking into account three key complex features exhibited by real-world electricity pricing schemes: (i) time-varying prices (e.g., time-of-day pricing, spot pricing, or higher energy prices during coincident peaks) and (ii) separate charge for peak power consumption. Our focus is on demand modulation at the granularity of an entire data center or a large part of it. For computational tractability reasons, we work with a fluid model for power demands which we imagine can be modulated using two abstract knobs of demand dropping and demand delaying (each with its associated penalties or costs). Given many data center workloads and electric prices can be effectively predicted using statistical modeling techniques, we devise a stochastic dynamic program (SDP) that can leverage such predictive models. Since the SDP can be computationally infeasible in many real platforms, we devise approximations for it. We also devise fully online algorithms that might be useful for scenarios with poor power demand or utility price predictability. For one of our online algorithms, we prove a competitive ratio of 2-1/n. Finally, using empirical evaluation with both real-world and synthetic power demands and real-world prices, we demonstrate the efficacy of our techniques. As two salient empirically-gained insights: (i) demand delaying is more effective than demand dropping regarding to peak shaving (e.g., 10.74% cost saving with only delaying vs. 1.45% with only dropping for Google workload) and (ii) workloads tend to have different cost saving potential under various electricity tariffs (e.g., 16.97% cost saving under peak-based tariff vs. 1.55% under time-varying pricing tariff for Facebook workload).