Y
Yangqiu Song
Researcher at Hong Kong University of Science and Technology
Publications - 290
Citations - 9551
Yangqiu Song is an academic researcher from Hong Kong University of Science and Technology. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 42, co-authored 248 publications receiving 7201 citations. Previous affiliations of Yangqiu Song include Microsoft & Urbana University.
Papers
More filters
Journal ArticleDOI
Parallel Spectral Clustering in Distributed Systems
TL;DR: This work investigates two representative ways of approximating the dense similarity matrix and picks the strategy of sparsifying the matrix via retaining nearest neighbors and investigates its parallelization, which can effectively handle large problems.
Proceedings ArticleDOI
Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks
TL;DR: This paper introduces the concept of meta-graph to HIN-based recommendation, and solves the information fusion problem with a "matrix factorization + factorization machine (FM)" approach, and proposes to use FM with Group lasso (FMG) to automatically learn from the observed ratings to effectively select useful meta- graph based features.
Journal ArticleDOI
TextFlow: Towards Better Understanding of Evolving Topics in Text
TL;DR: This paper introduces TextFlow, a seamless integration of visualization and topic mining techniques, for analyzing various evolution patterns that emerge from multiple topics, and extends an existing analysis technique to extract three-level features.
Proceedings ArticleDOI
Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN
TL;DR: A graph-CNN based deep learning model is proposed to first convert texts to graph-of-words, and then use graph convolution operations to convolve the word graph and regularize the deep architecture with the dependency among labels.
Proceedings Article
MetaGAN: an adversarial approach to few-shot learning
TL;DR: This paper proposes a conceptually simple and general framework called MetaGAN for few-shot learning problems, and shows that with this MetaGAN framework, it can extend supervised few- shot learning models to naturally cope with unlabeled data.