Sunwei

M.Sc. Student @ IIP Group
Department of Computer Science and Technology
Nanjing University

Email: weisun_@outlook.com

Supervisor

Biography

I received my B.Sc. degree in of Soochow University in June 2017. In the same year, I was admitted to study for a Master degree in Nanjing University without entrance examination. Currently I am a second year M.Sc. student of Department of Computer Science and Technology in Nanjing University and a member of IIP Group, led by professor Jun-Yuan Xie and Chong-Jun Wang.

Research Interest

I am interested in Machine Learning and Multi-label Learning.
Specifically, now my first work is to exploit label correlations on multi-label learning, i.e. On Multi-label Text Classification (MLTC), text features can be regarded as detailed description of documents and label sets can be a summarization of documents. Hybrid Topics from text features and label sets by LDA (a method of topic model) can effectively represent the whole label correlations.
My second work is to apply deep learning to multi-label text classification. We utilize dilated convolution to obtain the semantic understanding of the text and design a hybrid attention mechansim for different labels (Specifically, each label should attend to most relevant textual information). First, we initialize trainable label embeddings. We obation word-level information base on Bi-LSTM and get semantic understanding of a document based on word-level information. Then, we design a hybrid attention for different labels based on label embeddings. Besides, we add label cooccurrence matrix into loss function to guide the whole network to learn and achieve good results.

Resources

Extreme Classiﬁcation Repository: for large-scale multi-label datasets and off-the-shelf eXtreme Multi-Label Learning (XML) solvers.
Mulan Multi-Label Learning Datasets: regular/traditional multi-label learning datasets.
Related Works: This page categorizes a list of works of my interest, mainly in Multi-Label Learning.

Rewards or Honors

南京大学IIP