Di Niu @ University of Alberta

Last updated: May 1, 2019

 
 

Short Bio


I’m an Associate Professor in the Department of Electrical and Computer Engineering at University of Alberta.  I did my PhD work in iQua Research Group, the Department of Electrical and Computer Engineering at University of Toronto, from 2008 to 2012, and was a M.A.Sc. student in the same department from 2006 to 2008. I received the B.Eng. degree in 2005 from the Department of Electronics and Communication Engineering, Sun Yat-sen (Zhongshan) University, Guangzhou, Guangdong, China. Now I’m leading a team of graduate students working on exciting topics in the cross-disciplinary areas of applied statistics, optimization, data mining, and networked/distributed systems.

Associate Professor

Department of Electrical and Computer Engineering, University of Alberta

Edmonton, Alberta, Canada


Research Areas: data mining and applied machine learning, cloud computing and big data analytics,  parallel and distributed systems, text mining and natural language processing, statistical learning. 


Methodologies: optimization, statistical machine learning, parallel and distributed algorithms, matrix learning, text modeling, data mining, deep neural networks, distributed systems.

Contact me

Email: dniu@ualberta.ca

Office: D-ICE, 11-361

Curriculum Vitae

Can be provided upon request.


To Prospective Students


I encourage self-motivated students that are interested in working with me to contact me through email 2-3 months before you plan to submit your application to University of Alberta.

Ongoing Research Projects


Currently, Di is actively working with his PhD and Master’s students on the following topics, in collaboration with a few industrial partners (mainly including Tencent and Wedge Networks) and other academic institutes (mainly including University of Toronto):


-Text modeling, understanding and recommendation, text matching, information retrieval, event discovery and summarization, storyline generation and empirical natural language processing in general.


-Distributed machine learning and data analytics processing algorithms and platforms, with a focus on both algorithm design and innovative system development. The specific problems we study include distributed algorithms for training machine learning models, such as deep neural networks and matrix factorization, model training for decentralized data and distributed architectures for streaming analytics and batch job processing.


-Machine learning, data mining, data generation, data quality assessment.

News

Paper accepted to ACL 2019 (on matching document pairs with GCN)

Papers accepted to KDD 2019 (on distributed ML, concept mining, and related search recommendation)

Awarded NSERC Discovery Grant for proposal titled “Distributed Optimization for Machine Learning on Decentralized Data and Features”

Papers accepted to WWW 2019 (on natural language question generation, and search query generation)

Papers accepted to AAAI 2019, INFOCOM 2019, and TPDS

Paper accepted to KDD 2018 (on natural language sentence matching)
Paper accepted to WWW 2018 (on natural language sentence matching)

Won the Extraordinary Achievement Award (top 1 out of 18 grant holders) for 2016-2017 CCF-Tencent Rhino Bird Open Grant, on CNCC, Oct 27, Fuzhou China.

Paper accepted to IEEE ICDM 2017 (on cellular activity prediction and spatial data mining )

Paper accepted to ACM CIKM 2017 (on story generation from text documents)

Paper accepted to ACM SoCC 2017 (on latency optimization in cloud storage)

Papers accepted to IEEE INFOCOM 2017 (on web service latency modeling and OvS multicast)

Papers accepted to ACM TOMPECS (on cloud computing, another on video storage)

Paper accepted to AAAI 2017 (on quantile regression in matrix factorization)
Paper accepted to IEEE ICDM 2016 (on house price modeling)

Paper accepted to IEEE Trans. on Parallel and Distributed Systems (on data transfer in clusters)

Paper accepted to IEEE/ACM Trans. on Networking (on mobile network latency modeling)

Paper accepted to ACM CIKM 2016 (on large-scale video recommendation)