Contact me at: josh [dot] nguyen [at] anu [dot] edu [dot] au

I am an MPhil student at the Computational Media Lab, the Australian National University, supervised by Lexing Xie and Colin Klein. I am interested in how dilemmas come about, are presented and are justified on social media, and how to automate the reasoning process similar to that observable on online forums.

Previously I graduated with a BSc in computer science from the School of Computing and Information Systems, the University of Melbourne, Australia.

In the summer of 2019 and winter of 2020, I worked as an intern at the School of Computer Science, the University of Sydney, under the supervision of Dr. Nguyen Tran. Our projects focused on distributed optimization and personalization, with an emphasis on designing communication-efficient distributed ML algorithms for federated learning (FL). If you are interested, I suggest taking a look at this comprehensive survey about FL.

During my undergraduate studies, I also worked with Dr. Charl Ras at the School of Mathematics and Statistics, the University of Melbourne.

I publish under my official Vietnamese name, Tuan Dung Nguyen.


[12-05-2022] I gave a talk on our ICWSM 2022 paper at the ANU’s AI, ML and Friends seminar. The slides can be found here.

[16-03-2022] Our paper, Mapping Topics in 100,000 Real-life Moral Dilemmas, is accepted to ICWSM 2022! The code can be found here and data here.

[30-11-2021] I am honored to attend the International School in Artificial Intelligence and its Applications in Computer Science (ISAAC 2021) this december at Monash University.

[27-04-2021] I will be volunteering at the ICWSM-2021 conference.

[19-04-2021] I will be volunteering at the AIES-2021 conference. Thanks HMI for your invitation.

[16-04-2021] I am honored to be selected to the Cornell, Maryland and Max Planck Pre-doctoral Research School (CMMRS-21).

[15-12-2020] Check out our pre-print DONE: Distributed Newton-type Method for Federated Edge Learning on arXiv.

[26-10-2020] Our work, titled Personalized Federated Learning with Moreau Envelopes, is accepted to NeurIPS 2020. The code can be found here.

[26-05-2020] Our paper, Federated Learning with Proximal Stochastic Variance Reduced Gradient Algorithms, is accepted to ICPP 2020.