SCALE@NTU Research Webinar Feb 2022

This research webinar on Teams is organized by Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU) to share the research work in the Corp Lab. For registration, please visit:

https://wis.ntu.edu.sg/pls/webexe88/REGISTER_NTU.REGISTER?EVENT_ID=OA22021015095741

Talk 1:  Learning Scenario Representation for Solving Two-stage Stochastic Integer Programs

Many practical combinatorial optimization problems under uncertainty can be modeled as stochastic integer programs (SIPs), which are extremely challenging to solve due to the high complexity. To solve two-stage SIPs efficiently, we propose a conditional variational autoencoder (CVAE) based method to learn scenario representation for a class of SIP instances. Specifically, we design a graph convolutional network based encoder to embed each scenario with the deterministic part of its instance (i.e. context) into a low-dimensional latent space, from which a decoder reconstructs the scenario from its latent representation conditioned on the context. Such a design effectively captures the dependencies of the scenarios on their corresponding instances. We apply the trained encoder to two tasks in typical SIP solving, i.e. scenario reduction and objective prediction. Experiments on two graph-based SIPs show that the learned representation significantly boosts the solving performance to attain high-quality solutions in short computational time, and generalizes fairly well to problems of larger sizes or with more scenarios.

Speaker:  Wu Yaoxin, Research Associate, SCALE@NTU

Yaoxin Wu received his B.Eng. degree in traffic engineering from Wuyi University, China, in 2015, and M.Eng. degree in control engineering from Guangdong University of Technology, China, in 2018. He is currently a Ph.D. student with School of Computer Science and Engineering, Nanyang Technological University, Singapore, and a Research Associate with Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU). His research interests include combinatorial optimization problems, graph neural networks, and deep (reinforcement) learning.

Talk 2:  CFR-MIX: Solving Imperfect Information Extensive-Form Games with Combinatorial Action Space

In many real-world scenarios, a team of agents coordinate with each other to compete against an opponent. The challenge of solving this type of game is that the team’s joint action space grows exponentially with the number of agents, which results in the inefficiency of the existing algorithms, e.g., Counterfactual Regret Minimization (CFR). In this talk, we will introduce a new framework of deep CFR: CFR-MIX to address this problem. In this framework, we first propose a new strategy representation and a consistency relationship to maintain the cooperation between team players. Then we transform the consistency relationship between strategies to the consistency relationship between the cumulative regret values. Furthermore, we propose a novel decomposition method over cumulative regret values to guarantee the consistency relationship. Finally, we employ a mixing layer under Deep CFR framework to form CFR-MIX algorithm. Experimental results show that CFR-MIX outperforms existing methods on various games significantly.

Speaker:  Li Shuxin, Research Associate, SCALE@NTU

Shuxin Li received her Master of Engineering degree from Tianjin University in Jan 2018. Since Nov 2019, she has been a Research Associate at Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU). Her research interests include game theory and large-scale security game solving.