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
Research Topics
Deep Learning

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

Master's Research - McGill University
PhD - McGill University
Co-supervisor :
PhD - McGill University
Co-supervisor :
PhD - McGill University
PhD - McGill University
PhD - McGill University
PhD - McGill University
PhD - McGill University
PhD - McGill University
Master's Research - McGill University
Master's Research - McGill University
PhD - McGill University
Co-supervisor :
Master's Research - McGill University
Postdoctorate - McGill University
Co-supervisor :
PhD - McGill University

Publications

ICE-SEARCH: A Language Model-Driven Feature Selection Approach
Tianze Yang
Tianyi Yang
Shaoshan Liu
Fuyuan Lyu
This study unveils the In-Context Evolutionary Search (ICE-SEARCH) method, the first work that melds language models (LMs) with evolutionary… (see more) algorithms for feature selection (FS) tasks and demonstrates its effectiveness in Medical Predictive Analytics (MPA) applications. ICE-SEARCH harnesses the crossover and mutation capabilities inherent in LMs within an evolutionary framework, significantly improving FS through the model's comprehensive world knowledge and its adaptability to a variety of roles. Our evaluation of this methodology spans three crucial MPA tasks: stroke, cardiovascular disease, and diabetes, where ICE-SEARCH outperforms traditional FS methods in pinpointing essential features for medical applications. ICE-SEARCH achieves State-of-the-Art (SOTA) performance in stroke prediction and diabetes prediction; the Decision-Randomized ICE-SEARCH ranks as SOTA in cardiovascular disease prediction. Our results not only demonstrate the efficacy of ICE-SEARCH in medical FS but also underscore the versatility, efficiency, and scalability of integrating LMs in FS tasks. The study emphasizes the critical role of incorporating domain-specific insights, illustrating ICE-SEARCH's robustness, generalizability, and swift convergence. This opens avenues for further research into comprehensive and intricate FS landscapes, marking a significant stride in the application of artificial intelligence in medical predictive analytics.
AICOM-MP: an AI-based Monkeypox Detector for Resource-Constrained Environments
Tianyi Yang
Tianze Yang
Andrew Liu
Jie Tang
Na An
Shaoshan Liu
Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation
Chengming Hu
Haolun Wu
Xuan Li
Chen Ma
Xi Chen
Jun Yan
Boyu Wang
AdaTeacher: Adaptive Multi-Teacher Weighting for Communication Load Forecasting
Chengming Hu
Ju Wang
Di Wu
Yan Xin
Charlie Zhang
To deal with notorious delays in communication systems, it is crucial to forecast key system characteristics, such as the communication load… (see more). Most existing studies aggregate data from multiple edge nodes for improving the forecasting accuracy. However, the bandwidth cost of such data aggregation could be unacceptably high from the perspective of system operators. To achieve both the high forecasting accuracy and bandwidth efficiency, this paper proposes an Adaptive Multi-Teacher Weighting in Teacher-Student Learning approach, namely AdaTeacher, for communication load forecasting of multiple edge nodes. Each edge node trains a local model on its own data. A target node collects multiple models from its neighbor nodes and treats these models as teachers. Then, the target node trains a student model from teachers via Teacher-Student (T-S) learning. Unlike most existing T-S learning approaches that treat teachers evenly, resulting in a limited performance, AdaTeacher introduces a bilevel optimization algorithm to dynamically learn an importance weight for each teacher toward a more effective and accurate T-S learning process. Compared to the state-of-the-art methods, Ada Teacher not only reduces the bandwidth cost by 53.85%, but also improves the load forecasting accuracy by 21.56% and 24.24% on two real-world datasets.
Energy Saving in Cellular Wireless Networks via Transfer Deep Reinforcement Learning
Di Wu
Yi Tian Xu
M. Jenkin
Seowoo Jang
Ekram Hossain
With the increasing use of data-intensive mobile applications and the number of mobile users, the demand for wireless data services has been… (see more) increasing exponentially in recent years. In order to address this demand, a large number of new cellular base stations are being deployed around the world, leading to a significant increase in energy consumption and greenhouse gas emission. Consequently, energy consumption has emerged as a key concern in the fifth-generation (5G) network era and beyond. Reinforcement learning (RL), which aims to learn a control policy via interacting with the environment, has been shown to be effective in addressing network optimization problems. However, for reinforcement learning, especially deep reinforcement learning, a large number of interactions with the environment are required. This often limits its applicability in the real world. In this work, to better deal with dynamic traffic scenarios and improve real-world applicability, we propose a transfer deep reinforcement learning framework for energy optimization in cellular communication networks. Specifically, we first pre-train a set of RL-based energy-saving policies on source base stations and then transfer the most suitable policy to the given target base station in an unsupervised learning manner. Experimental results demonstrate that base station energy consumption can be reduced significantly using this approach.
Learning to Adapt: Communication Load Balancing via Adaptive Deep Reinforcement Learning
Di Wu
Yi Tian Xu
Jimmy Li
M. Jenkin
Ekram Hossain
Seowoo Jang
Yan Xin
Charlie Zhang
The association of mobile devices with network resources (e.g., base stations, frequency bands/channels), known as load balancing, is critic… (see more)al to reduce communication traffic congestion and network performance. Reinforcement learning (RL) has shown to be effective for communication load balancing and achieves better performance than currently used rule-based methods, especially when the traffic load changes quickly. However, RL-based methods usually need to interact with the environment for a large number of time steps to learn an effective policy and can be difficult to tune. In this work, we aim to improve the data efficiency of RL-based solutions to make them more suitable and applicable for real-world applications. Specifically, we propose a simple, yet efficient and effective deep RL-based wireless network load balancing framework. In this solution, a set of good initialization values for control actions are selected with some cost-efficient approach to center the training of the RL agent. Then, a deep RL-based agent is trained to find offsets from the initialization values that optimize the load balancing problem. Experimental evaluation on a set of dynamic traffic scenarios demonstrates the effectiveness and efficiency of the proposed method.
Realizing XR Applications Using 5G-Based 3D Holographic Communication and Mobile Edge Computing
Dun Yuan
Ekram Hossain
Di Wu
3D holographic communication has the potential to revolutionize the way people interact with each other in virtual spaces, offering immersiv… (see more)e and realistic experiences. However, demands for high data rates, extremely low latency, and high computations to enable this technology pose a significant challenge. To address this challenge, we propose a novel job scheduling algorithm that leverages Mobile Edge Computing (MEC) servers in order to minimize the total latency in 3D holographic communication. One of the motivations for this work is to prevent the uncanny valley effect, which can occur when the latency hinders the seamless and real-time rendering of holographic content, leading to a less convincing and less engaging user experience. Our proposed algorithm dynamically allocates computation tasks to MEC servers, considering the network conditions, computational capabilities of the servers, and the requirements of the 3D holographic communication application. We conduct extensive experiments to evaluate the performance of our algorithm in terms of latency reduction, and the results demonstrate that our approach significantly outperforms other baseline methods. Furthermore, we present a practical scenario involving Augmented Reality (AR), which not only illustrates the applicability of our algorithm but also highlights the importance of minimizing latency in achieving high-quality holographic views. By efficiently distributing the computation workload among MEC servers and reducing the overall latency, our proposed algorithm enhances the user experience in 3D holographic communications and paves the way for the widespread adoption of this technology in various applications, such as telemedicine, remote collaboration, and entertainment.
A Generic Framework for Byzantine-Tolerant Consensus Achievement in Robot Swarms
Hanqing Zhao
Alexandre Pacheco
Volker Strobel
Andreagiovanni Reina
Marco Dorigo
Recent studies show that some security features that blockchains grant to decentralized networks on the internet can be ported to swarm robo… (see more)tics. Although the integration of blockchain technology and swarm robotics shows great promise, thus far, research has been limited to proof-of-concept scenarios where the blockchain-based mechanisms are tailored to a particular swarm task and operating environment. In this study, we propose a generic framework based on a blockchain smart contract that enables robot swarms to achieve secure consensus in an arbitrary observation space. This means that our framework can be customized to fit different swarm robotics missions, while providing methods to identify and neutralize Byzantine robots, that is, robots which exhibit detrimental behaviours stemming from faults or malicious tampering.
Zero-Shot Fault Detection for Manipulators Through Bayesian Inverse Reinforcement Learning
We consider the detection of faults in robotic manipulators, with particular emphasis on faults that have not been observed or identified in… (see more) advance, which naturally includes those that occur very infrequently. Recent studies indicate that the reward function obtained through Inverse Reinforcement Learning (IRL) can help detect anomalies caused by faults in a control system (i.e. fault detection). Current IRL methods for fault detection, however, either use a linear reward representation or require extensive sampling from the environment to estimate the policy, rendering them inappropriate for safety-critical situations where sampling of failure observations via fault injection can be expensive and dangerous. To address this issue, this paper proposes a zero-shot and exogenous fault detector based on an approximate variational reward imitation learning (AVRIL) structure. The fault detector recovers a reward signal as a function of externally observable information to describe the normal operation, which can then be used to detect anomalies caused by faults. Our method incorporates expert knowledge through a customizable reward prior distribution, allowing the fault detector to learn the reward solely from normal operation samples, without the need for a simulator or costly interactions with the environment. We evaluate our approach for exogenous partial fault detection in multi-stage robotic manipulator tasks, comparing it with several baseline methods. The results demonstrate that our method more effectively identifies unseen faults even when they occur within just three controller time steps.
Importance-aware Co-teaching for Offline Model-based Optimization
Ye Yuan
Can Chen
Zixuan Liu
Willie Neiswanger
Importance-aware Co-teaching for Offline Model-based Optimization
Ye Yuan
Can Chen
Zixuan Liu
Willie Neiswanger
Offline model-based optimization aims to find a design that maximizes a property of interest using only an offline dataset, with application… (see more)s in robot, protein, and molecule design, among others. A prevalent approach is gradient ascent, where a proxy model is trained on the offline dataset and then used to optimize the design. This method suffers from an out-of-distribution issue, where the proxy is not accurate for unseen designs. To mitigate this issue, we explore using a pseudo-labeler to generate valuable data for fine-tuning the proxy. Specifically, we propose
Parallel-mentoring for Offline Model-based Optimization
Can Chen
Christopher Beckham
Zixuan Liu