Portrait of Xue (Steve) Liu is unavailable

Xue (Steve) Liu

Associate Academic Member
Full Professor, McGill University, School of Computer Science
Vice President Research and Development, Chief Scientist and Co-Director, Samsung's Montreal AI Center

Biography

Xue (Steve) Liu is an associate academic member of Mila – Quebec Artificial Intelligence Institute and full professor at McGill University’s School of Computer Science.

He is also a William Dawson Scholar at McGill, as well as a professor (courtesy appointment) in the Department of Mathematics and Statistics, associate member of the Centre for Intelligent Machines (CIM), and associate member of the Centre for Advanced Systems and Technologies in Communications (SYTACom).

Liu is VP of R&D, chief scientist and co-director of Samsung AI Center Montréal. Before that, he was chief scientist in charge of research and innovation at Tinder Inc., the world’s largest dating and social discovery app, then valued at over US$10 billion.

He is a Fellow of the IEEE and the Canadian Academy of Engineering in addition to being the recipient of many awards, including the 2017 Mitacs Award for Exceptional Leadership – Professor; Outstanding Young Canadian Computer Science Researcher Prize from the Canadian Association of Computer Science (2014); and McGill’s Tomlinson Scientist Award for “recognition of excellence and scientific leadership.” He founded McGill’s Cyber-Physical Intelligence Lab in 2007 and still serves as its director.

Liu also briefly served as Samuel R. Thompson Chair Associate Professor in the Department of Computer Science and Engineering at the University of Nebraska-Lincoln, and worked at Hewlett-Packard Labs in Palo Alto (California) and IBM’s Thomas J. Watson Research Center (New York)

Current Students

Alejandro Salinas-Medina
PhD - McGill University
alejandro.salinas-medina@mila.quebec
Website
Github
Google Scholar
Can (Sam) Chen
PhD - McGill University
Co-supervisor :
Chris Pal
can.chen@mila.quebec
Website
Chengming Hu
PhD - McGill University
chengming.hu@mila.quebec
Dheeraj Vattikonda
Master's Research - McGill University
dheeraj.vattikonda@mila.quebec
Dun Yuan
Master's Research - McGill University
dun.yuan@mila.quebec
Gaspard Zhao
Postdoctorate - McGill University
Co-supervisor :
Gregory Dudek
hanqing.zhao@mila.quebec
Website
Mark Bai
Master's Research - McGill University
mark.bai@mila.quebec
Github
Haolun Wu
PhD - McGill University
haolun.wu@mila.quebec
Website
Junliang Luo
PhD - McGill University
junliang.luo@mila.quebec
Github
Lyu Fuyuan
PhD - McGill University
Co-supervisor :
Jin Guo
fuyuan.lyu@mila.quebec
Website
Github
Google Scholar
Rishabh Thaney
Master's Research - McGill University
rishabh.thaney@mila.quebec
Github
Shaoxiang Qin
PhD - McGill University
shaoxiang.qin@mila.quebec
Shuhao Zheng
PhD - McGill University
shuhao.zheng@mila.quebec
Xuan Li
PhD - McGill University
xuan.li@mila.quebec
Ye Yuan
PhD - McGill University
ye.yuan@mila.quebec
Website
Github
Google Scholar
Yili Jin
PhD - McGill University
yili.jin@mila.quebec
Website
Google Scholar
Ralph Cui
Postdoctorate
yufei.cui@mila.quebec
Website
Google Scholar
Zonglun Li
PhD - McGill University
zonglun.li@mila.quebec

Publications

Smart Futures Based Resource Trading and Coalition Formation for Real-Time Mobile Data Processing
Ruitao Chen
Xianbin Wang
Xue (Steve) Liu
Collaboration among mobile devices (MDs) is becoming more important, as it could augment computing capacity at the network edge through peer… (see more)-to-peer service provisioning, and directly enhance real-time computational performance in smart Internet-of-Things applications. As an important aspect of collaboration mechanism, conventional resource trading (RT) among MDs relies on an onsite interaction process, i.e., price negotiation between service providers and requesters, which, however, inevitably incurs excessive latency and degrades RT efficiency. To overcome this challenge, this article adopts the concept of futures contract (FC) used in financial market, and proposes a smart futures for low latency RT. This new technique enables MDs to form trading coalitions and negotiate multilateral forward contracts applied to a collaboration term in the future. To maximize the benefits of self-interested MDs, the negotiation process of FC is modelled as a coalition formation game comprised of three components executed in an iterative manner, i.e., futures resource allocation, revenue sharing and payment allocation, and distributed decision-making of individual MD. Additionally, a FC enforcement scheme is implemented to efficiently manage the onsite resource sharing via recording resource balances of different task-types and MDs. Simulation results prove the superiority of smart futures in RT latency reduction and trading fairness provisioning.
2021-02-18
IEEE Transactions on Services Computing (published)
doi.org
Smart Futures Based Resource Trading and Coalition Formation for Real-Time Mobile Data Processing
Ruitao Chen
Xianbin Wang
Xue (Steve) Liu
Collaboration among mobile devices (MDs) is becoming more important, as it could augment computing capacity at the network edge through peer… (see more)-to-peer service provisioning, and directly enhance real-time computational performance in smart Internet-of-Things applications. As an important aspect of collaboration mechanism, conventional resource trading (RT) among MDs relies on an onsite interaction process, i.e., price negotiation between service providers and requesters, which, however, inevitably incurs excessive latency and degrades RT efficiency. To overcome this challenge, this article adopts the concept of futures contract (FC) used in financial market, and proposes a smart futures for low latency RT. This new technique enables MDs to form trading coalitions and negotiate multilateral forward contracts applied to a collaboration term in the future. To maximize the benefits of self-interested MDs, the negotiation process of FC is modelled as a coalition formation game comprised of three components executed in an iterative manner, i.e., futures resource allocation, revenue sharing and payment allocation, and distributed decision-making of individual MD. Additionally, a FC enforcement scheme is implemented to efficiently manage the onsite resource sharing via recording resource balances of different task-types and MDs. Simulation results prove the superiority of smart futures in RT latency reduction and trading fairness provisioning.
2021-02-18
IEEE Transactions on Services Computing (published)
doi.org
Variational Nested Dropout
Yufei Cui
Yushun Mao
Ziquan Liu
Qiao Li
Antoni Bert Chan
Xue (Steve) Liu
Tei-Wei Kuo
Chun Jason Xue
Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance du… (see more)ring training. It has been explored for: I. Constructing nested nets Cui et al. 2020, Cui et al. 2021: the nested nets are neural networks whose architectures can be adjusted instantly during testing time, e.g., based on computational constraints. The nested dropout implicitly ranks the network parameters, generating a set of sub-networks such that any smaller sub-network forms the basis of a larger one. II. Learning ordered representation Rippel et al. 2014: the nested dropout applied to the latent representation of a generative model (e.g., auto-encoder) ranks the features, enforcing explicit order of the dense representation over dimensions. However, the dropout rate is fixed as a hyper-parameter during the whole training process. For nested nets, when network parameters are removed, the performance decays in a human-specified trajectory rather than in a trajectory learned from data. For generative models, the importance of features is specified as a constant vector, restraining the flexibility of representation learning. To address the problem, we focus on the probabilistic counterpart of the nested dropout. We propose a variational nested dropout (VND) operation that draws samples of multi-dimensional ordered masks at a low cost, providing useful gradients to the parameters of nested dropout. Based on this approach, we design a Bayesian nested neural network that learns the order knowledge of the parameter distributions. We further exploit the VND under different generative models for learning ordered latent distributions. In experiments, we show that the proposed approach outperforms the nested network in terms of accuracy, calibration, and out-of-domain detection in classification tasks. It also outperforms the related generative models on data generation tasks.
2021-01-27
ArXiv (preprint)
doi.org
arxiv.org