Z
Zhongqi Lu
Researcher at Hong Kong University of Science and Technology
Publications - 15
Citations - 856
Zhongqi Lu is an academic researcher from Hong Kong University of Science and Technology. The author has contributed to research in topics: Recommender system & Transfer of learning. The author has an hindex of 9, co-authored 13 publications receiving 720 citations.
Papers
More filters
Proceedings Article
Heterogeneous transfer learning for image classification
TL;DR: This paper proposes a heterogeneous transfer learning framework for knowledge transfer between text and images by enriching the representation of the target images with semantic concepts extracted from the auxiliary source data through a novel matrix factorization method.
Proceedings Article
Content-based collaborative filtering for news topic recommendation
TL;DR: This paper proposes a Content-based Collaborative Filtering approach (CCF), which makes recommendations based on the rich contexts of the news and collaboratively analyzes the scarce feedbacks from the long-tail users.
Proceedings Article
Active transfer learning for cross-system recommendation
TL;DR: This paper proposes a framework to construct entity correspondence with limited budget by using active learning to facilitate knowledge transfer across recommender systems, and first iteratively select entities in the target system based on a proposed criterion to query their correspondences in the source system.
Proceedings Article
Selective Transfer Learning for Cross Domain Recommendation
TL;DR: This paper proposes a novel criterion based on empirical prediction error and its variance to better capture the consistency across domains in CF settings and embeds this criterion into a boosting framework to perform selective knowledge transfer.
Proceedings Article
Matrix factorization+ for movie recommendation
TL;DR: A novel model for movie recommendations using additional visual features extracted from pictural data like posters and still frames, to better understand movies is presented and leads to significant improvement over several state-of-the-art methods.