J
Jun Ma
Researcher at Shandong University
Publications - 109
Citations - 1761
Jun Ma is an academic researcher from Shandong University. The author has contributed to research in topics: Ranking (information retrieval) & Recommender system. The author has an hindex of 19, co-authored 105 publications receiving 1404 citations.
Papers
More filters
Journal ArticleDOI
Transparent conducting ZnO:Al films deposited on organic substrates deposited by r.f. magnetron-sputtering
TL;DR: In this paper, a transparent conducting ZnO:Al film with good adhesion and low resistivity has been prepared on organic substrates by r.f. magnetron-sputtering.
Proceedings ArticleDOI
A Collaborative Session-based Recommendation Approach with Parallel Memory Modules
TL;DR: This work proposes a Collaborative Session-based Recommendation Machine (CSRM), a novel hybrid framework to apply collaborative neighborhood information to session-based recommendations that demonstrates the effectiveness of CSRM compared to state-of-the-art session- based recommender systems.
Journal ArticleDOI
Ranking the spreading ability of nodes in complex networks based on local structure
TL;DR: A local structural centrality measure is proposed which considers both the number and the topological connections of the neighbors of a node, and can rank the spreading ability of nodes more accurately than centrality measures such as degree, k-shell, betweenness, closeness and local centrality.
Proceedings ArticleDOI
Modeling and Predicting Retweeting Dynamics on Microblogging Platforms
Shuai Gao,Jun Ma,Zhumin Chen +2 more
TL;DR: The proposed model explicitly characterizes the process through which a message gain its retweets, by capturing a power-law temporal relaxation function corresponding to the aging in the ability of the message to attract new retwets and an exponential reinforcement mechanism characterizing the "richer-get-richer" phenomenon.
Proceedings ArticleDOI
π-Net: A Parallel Information-sharing Network for Shared-account Cross-domain Sequential Recommendations
TL;DR: A Parallel Information-sharing Network (π-Net) is proposed to simultaneously generate recommendations for two domains where user behaviors on two domains are synchronously shared at each timestamp and it is demonstrated that π-Net outperforms state-of-the-art baselines in terms of MRR and Recall.