Home

Shufeng Kong, PhD (University of Technology Sydney, Australia)
Associate Professor
School of Software Engineering
Sun Yat-sen University (中山大学), Guangdong, China

Research Consultant
Department of Computer Science
Cornell University, Ithaca, NY, USA
Please contact me at sk2299@cornell.edu (Preferred) or kongshf@mail.sysu.edu.cn

My research area is Artificial Intelligence (AI) with a focus on large-scale constraint-based reasoning, optimization, and machine learning (ML). Existing methods often struggle to scale up to large real-world problems that involve physics, hard constraints, and complex decision-making processes. The goal of my research is to advance AI to solve concrete real-world applications, focusing on integrating reasoning-based traditional AI and data-driven ML to address core questions in computational sustainability, including large-scale fishing portfolio optimization, species distribution modelling, and material discovery.

Research Interest

• Deep learning and reinforcement learning
• Multi-label classification and multi-target regression
• Constraint programming, probabilistic graphical model, and combinatorial optimization

Publications

* indicates corresponding author

• Shufeng Kong, Francesco Ricci, Dan Guevarra, Jeffrey B. Neaton, Carla P. Gomes, and John M. Gregoire (2022): Density of states prediction for materials discovery via contrastive learning from probabilistic embeddings. Nature Communications (Impact Factor: 14.92), 13(1)，1-12. (JCR Q1)
• Yanchen Deng, Shufeng Kong*, Caihua Liu, and Bo An (2022): Deep Attentive Belief Propagation: Integrating Reasoning and Learning for Solving Constraint Optimization Problems. In: the 36th Annual Conference on Neural Information Processing Systems (NeurIPS’22). Accepted, to appear. (CCF A)
• Junwen Bai, Shufeng Kong*, and Carla P. Gomes (2022): Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification. In: the 39th International Conference on Machine Learning (ICML’22). Accepted, to appear. (CCF A)
• Yanchen Deng, Shufeng Kong*, and Bo An (2022): Pretrained cost model for distributed constraint optimization problems. In: the 36th AAAI Conference on Artificial Intelligence (AAAI’22). pp. 9331-9340. (CCF A)
• Shufeng Kong, Dan Guevarra, Carla Gomes, and John Gregoire (2021): Materials representation and transfer learning for multi-property prediction. Applied Physics Reviews (Impact Factor: 19.162), 8(2). (JCR Q1)
• Wenting Zhao, Shufeng Kong, Junwen Bai, Daniel Fink, and Carla Gomes (2021): HOTVAE: Learning high-order label correlation for multi-label classification via attention-based variational autoencoders. In: the 35th AAAI Conference on Artificial Intelligence (AAAI’21), pp. 15016-15024. (CCF A)
• Shufeng Kong, Junwen Bai, Jae Hee Lee, Di Chen, Andrew Allyn, Michelle Stuart, Malin Pinsky, Kathy Mills and Carla Gomes (2020): Deep hurdle networks for zero-inflated multi-target regression: application to multiple species abundance estimation. In: the 29th International Joint Conference on Artificial Intelligence (IJCAI’20), pp. 4375-4381. (CCF A)
• Junwen Bai, Shufeng Kong and Carla Gomes (2020): Disentangled variational autoencoder based multi-label classification with covariance-aware multivariate probit model. In: the 29th International Joint Conference on Artificial Intelligence (IJCAI’20), pp. 4313-4321. (CCF A)
• Shufeng Kong, Jae Hee Lee and Sanjiang Li (2018): A new distributed algorithm for efficient generalized arc-consistency propagation. Autonomous agent and multi-agent systems (Impact Factor: 1.419), 32(5):569-601. (JCR Q3)
• Shufeng Kong, Jae Hee Lee and Sanjiang Li (2018): Multiagent simple temporal problem: the arc-consistency approach. In: the 32th AAAI Conference on Artificial Intelligence (AAAI’18), New Orleans, Louisiana, USA, February 2-7, 2018. (CCF A)
• Shufeng Kong, Jae Hee Lee and Sanjiang Li (2017): A deterministic distributed algorithm for reasoning with connected row-convex constraints. In: the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS’17), pp. 203-211. (CCF B)
• Shufeng Kong, Sanjiang Li and Michael Sioutis (2018): Exploring directional path-consistency for solving constraint networks. The Computer Journal (Impact Factor: 0.98), 61(9): 1138-1350. (JCR Q4)
• Shufeng Kong, Sanjiang Li, Yongming Li and Zhiguo Long (2015): On tree-preserving constraints. In: the 21st International Conference on Principles and Practice of Constraint Programming (CP’15), pp. 244-261. (CCF B)
• Shufeng Kong, Sanjiang Li, Yongming Li and Zhiguo Long (2017): On tree-preserving constraints. Annals of Mathematics and Artificial Intelligence (Impact Factor: 1.011), 81(3-4): 241-271. (JCR Q3)
• Carla P. Gomes, Junwen Bai, Yexiang Xue, Johan Bjorck, Brendan Rappazzo, Sebastian Ament, Richard Bernstein, Shufeng Kong, Santosh K. Suram, R. Bruce van Dover, John M. Gregoire (2019): CRYSTAL: a multi-agent AI system for automated mapping of materials’ crystal structures. MRS Communications (Impact Factor: 1.935), 9(2):600-608. (JCR Q4)