Shengcai Liu（刘晟材）

alt text 

Research Scientist, Institute of High Performance Computing (IHPC)
Agency for Science, Technology and Research (A*STAR)
 Address: 1 Fusionopolis Way, #16-16, Connexis North Tower, Singapore 138632
Email: liusc3 [AT] sustech [DOT] edu [DOT] cn

Short Biography

I received my B.Sc. and Ph.D. degrees in the School of Computer Science and Technology from the University of Science and Technology of China (USTC) in 2014 and 2020, respectively, under the supervision of Prof. Xin Yao from University of Birminghan and Prof. Ke Tang from USTC.

From Jan 2021 to Jan 2023, I was a Research Assistant Professor at the Department of Computer Science and Engineering (CSE), Southern University of Science and Technology (SUSTech). I am also a member of the Nature Inspired Computation and Applications Laboratory (NICAL) led by Prof. Xin Yao and Prof. Ke Tang.

From Jan 2023 to May 2023, I was a Visting Professor at the Institute of High Performance Computing (IHPC), A*STAR, Singapore. Currently I am a research scientist at IHPC. I am in collaboration with Prof. Yew-Soon Ong from Nanyang Technological University (NTU).

Research Interest

The utimate goal of my research is to develop theoretical foundations and practical tools for fully automating the process of algorithm design.

Now I am working on:

  • Automatic Algorithm Design by Evolutionary Computation, i.e., Algorithm Evolution

  • Robust and well-generalized Neural Combinatorial Optimizers (Learn to Optimize)

  • Highly-effective automatically-designed algorithms for adversarial attack and robustness

Recent News

  • Apr 9, 2023: One paper accepted by IEEE CIM

  • Jan 10, 2023: One paper accepted by ACM TIST

  • Nov 19, 2022: One paper accepted by AAAI’2023

  • Oct 9, 2022: One paper accepted by IEEE TETCI

  • Jul 18, 2022: I (together with Prof. Ke Tang) gave a tutorial “Learn to Optimize” at WCCI 2022.

Selected Publications [Google Scholar]

* indicates that I am the corresponding author

Preprints

  1. Ning Lu, Shengcai Liu*, Rui He, Qi Wang, and Ke Tang. Large Language Models can be Guided to Evade AI-Generated Text Detection. Arxiv preprint arXiv:2305.10847. [preprint PDF]

  2. Rui He, Shengcai Liu*, Jiahao Wu, Shan He, and Ke Tang. Multi-Domain Learning From Insufficient Annotations. Arxiv preprint arXiv:2305.02757. [preprint PDF]

  3. Ning Lu, Shengcai Liu*, Zhirui Zhang, Qi Wang, Haifeng Liu, and Ke Tang. Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend. Arxiv preprint arXiv:2302.02568. [preprint PDF]

  4. Xiasheng Ma, Shengcai Liu*, and Wenjing Hong. Automatic Construction of Parallel Algorithm Portfolios for Multi-objective Optimization. Arxiv preprint arXiv:2211.09498. [preprint PDF]

  5. Shengcai Liu, Ning Lu, Wenjing Hong, Chao Qian, and Ke Tang. Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization. ArXiv preprint arXiv:2111.01528. [preprint PDF]

Journal Papers

  1. Shengcai Liu, Yu Zhang, Ke Tang, and Xin Yao. How Good Is Neural Combinatorial Optimization? A Systematic Evaluation on the Traveling Salesman Problem. IEEE Computational Intelligence Magazine, 2023, Accepted [preprint PDF]

  2. Zeyu Dai, Shengcai Liu*, Qing Li, and Ke Tang. Saliency Attack: Towards Imperceptible Black-box Adversarial Attack. ACM Transactions on Intelligent Systems and Technology, 2023, 14(3): 1-20. [preprint PDF] [PDF]

  3. Rui He, Shengcai Liu*, Shan He, and Ke Tang. Multi-Domain Active Learning: Literature Review and Comparative Study. IEEE Transactions on Emerging Topics in Computational Intelligence, 2023, 7(3): 791-804 [preprint PDF] [PDF]

  4. Shengcai Liu, Ning Lu, Cheng Chen, and Ke Tang. Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2022, 30: 98-111. [preprint PDF] [PDF]

  5. Shengcai Liu, Peng Yang, and Ke Tang. Approximately Optimal Construction of Parallel Algorithm Portfolios by Evolutionary Intelligence (in Chinese). SCIENTIA SINICA Technologica, 2022, 52, DOI: 10.1360/SST-2021-0372. [preprint PDF]

  6. Shengcai Liu, Ke Tang, and Xin Yao. Memetic Search for Vehicle Routing with Simultaneous Pickup-Delivery and Time Windows. Swarm and Evolutionary Computation, 66: 100927, 2021 [preprint PDF] [PDF]

  7. Shengcai Liu, Ke Tang, Peng Yang, and Xin Yao. Few-shots Parallel Algorithm Portfolio Construction via Co-evolution. IEEE Transactions on Evolutionary Computation, 2021, 25(3): 595-607. [preprint PDF] [PDF]

  8. Shengcai Liu, Ke Tang, and Xin Yao. Generative Adversarial Construction of Parallel Portfolios. IEEE Transactions on Cybernetics, 2022, 52(2): 784-795. [preprint PDF] [PDF]

Conference Papers

  1. Shengcai Liu, Fu Peng, and Ke Tang. Reliable Robustness Evaluation via Automatically Constructed Attack Ensembles. In: Proceedings of The 37th AAAI Conference on Artificial Intelligence (AAAI’2023). [preprint PDF]

  2. Fu Peng, Shengcai Liu*, and Ke Tang. Training Quantized Deep Neural Networks via Cooperative Coevolution. In: Proceedings of the 13th International Conference on Swarm Intelligence (ICSI’2022), Xi'an, China, 2022, 81-93. [PDF]

  3. Kangfei Zhao, Shengcai Liu*, Yu Rong, and Jeffrey Xu Yu. Towards Feature-free TSP Solver Selection: A Deep Learning Approach. In: Proceedings of the 20th International Joint Conference on Neural Networks (IJCNN’2021), Virtual Event, 2021, 1-8. [PDF]

  4. Shengcai Liu, Ke Tang, and Xin Yao. On Performance Estimation in Automatic Algorithm Configuration. In: Proceedings of The 34th AAAI Conference on Artificial Intelligence (AAAI’2020), New York, NY, 2020, 2384-2391. [PDF]

  5. Shengcai Liu, Ke Tang, and Xin Yao. Automatic Construction of Parallel Portfolios via Explicit Instance Grouping. In: Proceedings of The 33rd AAAI Conference on Artificial Intelligence (AAAI’2019), Honululu, HI, 2019, 1560-1567. [PDF]

  6. Shengcai Liu, Yufan Wei, Ke Tang, A.K. Qin, and Xin Yao. Qos-aware Long-Term Based Service Composition in Cloud Computing. In: Proceedings of The 14th IEEE Congress on Evolutionary Computation (CEC’2015), Sendai, Japan, 2015, 3362-3369. [PDF]

Invited Talks

  1. Learn to Optimize @ The 2022 IEEE World Congress on Computational Intelligence (WCCI’2022). Jul 18, 2022. [Slides]

  2. Co-Evolved Parallel Algorithm Portfolios @ The 7th Workshop on Evolutionary Computation and Learning (ECOLE’2021). May 15, 2021.

  3. Algorithm Portfolios for Beginners @ Magic-Data (数据魔术师). Apr 6, 2021. (online)

Code & Datasets

VRPenstein: A highly-flexible and high-performance meta-heuristic with considerable large configuration space for the vehicle routing problems (VRP).

GA-EAX-restart: A restart version of the powerful Genetic Algorithm with Edge Assembly Crossover (GA-EAX by Nagata & Kobayashi). In our massive experiments, GA-EAX-restart could consistently outperform GA-EAX and LKH 2.0.9, the two state-of-the-art inexact solvers for TSP.

Community Services

One of the editors of All About Evolutionary Optimization (AAEO) (i.e., ECOLE weekly).

Journal reviewers: IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Evolutionary Computation, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Cybernetics, IEEE Transactions on Emerging Topics in Computational Intelligence, IEEE Computational Intelligence Magazine, ACM Transactions on Asian and Low-Resource Language Information Processing, Journal of Artificial Intelligence, Frontiers of Computer Science, Information Sciences, Memetic Computing, Natural Computing, Swarm and Evolutionary Optimization.

PC members: AAAI 2019/2020/2021/2022/2023, IJCAI 2020/2021/2022/2023, ICML 2021, NeurIPS 2021

Member: IEEE, AAAI