Maxime Roland René Flin
Reykjavik University, Iceland
Xueguang Ma, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Jimmy Lin
Neural retrieval systems have proven effective across a range of tasks and languages. However, creating fully zero-shot neural retrieval pipeline remains a challenge when relevance labels are not available.
Benyamin Jamialahmadi, Master’s candidate
David R. Cheriton School of Computer Science
Supervisors: Professors Ali Ghodsi, Mohammad Kohandel
Chris Trevisan, Undergraduate student
David R. Cheriton School of Computer Science
Fadhil Abubaker, Master’s candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Khuzaima Daudjee
Prabhjot Singh, Master’s candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Diogo Barradas
Although encrypted channels, like those provided by anonymity networks such as Tor, have been put into effect, network adversaries have proven their capability to undermine users’ browsing privacy through website fingerprinting attacks.
Shaokai Wang, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Bin Ma
Ibrahim Numanagić
Canada Research Chair in Data Science and Computational Biology
Assistant Professor, Department of Computer Science
University of Victoria
Robert Wang, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Lap Chi Lau
Sheng-Chieh (Jack) Lin, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Jimmy Lin
Contrastive learning is a commonly used technique to train an effective neural retrieval model; however, it requires much computation resources (i.e., multiple GPUs or TPUs).