R
Ruiming Tang
Researcher at Huawei
Publications - 178
Citations - 4429
Ruiming Tang is an academic researcher from Huawei. The author has contributed to research in topics: Computer science & Recommender system. The author has an hindex of 19, co-authored 116 publications receiving 2294 citations. Previous affiliations of Ruiming Tang include The Chinese University of Hong Kong & National University of Singapore.
Papers
More filters
Patent
Recommendation Method and Apparatus
TL;DR: In this article, an intelligent recommendation method, comprising of acquiring recommendation system state parameters according to multiple past historical recommended objects and the behaviors of a user for each historical recommended object, is presented, which facilitates the improvement of the recommendation efficiency and accuracy rate.
Patent
Topic recommending method and device
TL;DR: In this paper, the authors proposed a topic recommendation method based on the historical operation behavior of a sample user with respect to M objects and predicting a preference value of a target user to each object of the M objects according to historical operation behaviour of the sample user in each object.
Proceedings ArticleDOI
Integrated Ranking for News Feed with Reinforcement Learning
TL;DR: In this article , a new model named NFIRank (News Feed Integrated Ranking with reinforcement learning) is proposed to formulate the whole interaction session as a Markov Decision Process (MDP) and gain 1.58% improvements in CTR compared with the baseline in online A/B test.
Posted Content
Context-aware Reranking with Utility Maximization for Recommendation
TL;DR: Zhang et al. as mentioned in this paper proposed a pairwise re-ranking framework, Context-aware Reranking with Utility Maximization for recommendation (CRUM), which maximizes the overall utility after reranking efficiently.
Posted Content
Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation
TL;DR: In this article, a distance-based recommendation model is proposed to capture fine-grained preference information by parameterizing each user and item by Gaussian distributions to capture the learning uncertainties, and an adaptive margin generation scheme was proposed to generate the margins regarding different training triplets.