Xi Lin (林熙)

Xi Lin is currently a Post Doctoral Research Fellow with Department of Computer Science at the City University of Hong Kong, working with Prof. Qingfu Zhang. He received the B.Sc. degree from South China University of Technology, the M.A. degree from Columbia University, and the Ph.D. degree from City University of Hong Kong under the supervision of Prof. Qingfu Zhang and Prof. Sam Kwong.

His research interests include multi-objective optimization, learning based optimization, Bayesian optimization, evolutionary computation and multi-task learning. His work has been published in top-tier machine learning conferences such as ICML, NeurIPS and ICLR. He serves as an Action Editor for Transactions on Machine Learning Research (TMLR). He is a regular reviewer for many machine learning and evolutionary computation conferences and journals, and has received several outstanding reviewer awards from ICML, ICLR and TMLR.

Email  /  Google Scholar  /  Github

profile photo

Preprints

(*: equal contribution, __: student first author I co-mentor)
Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization
Xi Lin, Yilu Liu, Xiaoyuan Zhang, Fei Liu, Zhenkun Wang, Qingfu Zhang
pdf / arXiv
Instance-Conditioned Adaptation for Large-scale Generalization of Neural Combinatorial Optimization
Changliang Zhou*, Xi Lin*, Zhenkun Wang, Xialiang Tong, Mingxuan Yuan, Qingfu Zhang
pdf / arXiv
Self-Improved Learning for Scalable Neural Combinatorial Optimization
Fu Luo, Xi Lin, Zhenkun Wang, Xialiang Tong, Mingxuan Yuan, Qingfu Zhang
pdf / arXiv
PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
Ping Guo, Zhiyuan Yang, Xi Lin, Qingchuan Zhao, Qingfu Zhang
pdf / arXiv
Large Language Model for Multi-objective Evolutionary Optimization
Fei Liu, Xi Lin, Zhenkun Wang, Shunyu Yao, Xialiang Tong, Mingxuan Yuan, Qingfu Zhang
pdf / arXiv
Multi-Objective Evolution of Heuristic Using Large Language Model
Shunyu Yao*, Fei Liu*, Xi Lin, Zhichao Lu, Zhenkun Wang, Qingfu Zhang
pdf / arXiv

Survey and Package

(*: equal contribution, __: student first author I co-mentor)
A Systematic Survey on Large Language Models for Algorithm Design (New)
Fei Liu, Yiming Yao, Ping Guo, Zhiyuan Yang, Xi Lin, Xialiang Tong, Mingxuan Yuan, Zhichao Lu, Zhenkun Wang, Qingfu Zhang
pdf / arXiv
LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch (New)
Xiaoyuan Zhang*, Liang Zhao*, Yingying Yu*, Xi Lin, Zhenkun Wang, Han Zhao, Qingfu Zhang
Advances in Neural Information Processing Systems (NeurIPS) , 2024
pdf / arXiv / code

Selected Publications

(*: equal contribution, __: student first author I co-mentor, full list: Google Scholar)
Dealing with Structure Constraints in Evolutionary Pareto Set Learning
Xi Lin, Xiaoyuan Zhang, Zhiyuan Yang, Qingfu Zhang
IEEE Transactions on Evolutionary Computation, to appear
pdf / arXiv
Gliding over the Pareto Front with Uniform Designs
Xiaoyuan Zhang, Genghui Li, Xi Lin, Yichi Zhang, Yifan Chen, Qingfu Zhang
Advances in Neural Information Processing Systems (NeurIPS) , 2024
pdf / arXiv
Smooth Tchebycheff Scalarization for Multi-Objective Optimization
Xi Lin, Xiaoyuan Zhang, Zhiyuan Yang, Fei Liu, Zhenkun Wang, Qingfu Zhang
International Conference on Machine Learning (ICML), 2024
pdf / arXiv / openreview / code
Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
Fei Liu, Xialiang Tong, Mingxuan Yuan, Xi Lin, Fu Luo, Zhenkun Wang, Zhichao Lu, Qingfu Zhang
International Conference on Machine Learning (ICML), 2024 (Oral Presentation, Top 1.6% among All Submissions)
pdf / arXiv / openreview / code
Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Models
Rui Zhang, Fei Liu, Xi Lin, Zhenkun Wang, Zhichao Lu, Qingfu Zhang
International Conference on Parallel Problem Solving From Nature (PPSN), 2024
pdf / arXiv / code
Multi-Task Learning for Routing Problem with Cross-Problem Zero-Shot Generalization
Fei Liu, Xi Lin, Zhenkun Wang, Qingfu Zhang, Xialiang Tong, Mingxuan Yuan
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024
pdf / arXiv / code
Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization
Fu Luo*, Xi Lin*, Fei Liu, Qingfu Zhang, Zhenkun Wang
Advances in Neural Information Processing Systems (NeurIPS) , 2023
pdf / arXiv / openreview / code
Hypervolume Maximization: A Geometric View of Pareto Set Learning
Xiaoyuan Zhang, Xi Lin, Bo Xue, Yifan Chen, Qingfu Zhang
Advances in Neural Information Processing Systems (NeurIPS) , 2023
pdf / openreview
Continuation Path Learning for Homotopy Optimization
Xi Lin, Zhiyuan Yang, Xiaoyuan Zhang, Qingfu Zhang
International Conference on Machine Learning (ICML), 2023 (Oral Presentation, Top 2.4% among All Submissions)
pdf / arXiv / openreview / code
Pareto Set Learning for Expensive Multi-Objective Optimization
Xi Lin, Zhiyuan Yang, Xiaoyuan Zhang, Qingfu Zhang
Advances in Neural Information Processing Systems (NeurIPS) , 2022
pdf / arXiv / openreview / code
Pareto Set Learning for Neural Multi-Objective Combinatorial Optimization
Xi Lin, Zhiyuan Yang, Qingfu Zhang
International Conference on Learning Representations (ICLR) , 2022
pdf / arXiv / openreview / code
Controllable Pareto Multi-Task Learning
Xi Lin, Zhiyuan Yang, Qingfu Zhang, Sam Kwong
Technical Report, 2020
pdf / arXiv
Pareto Multi-Task Learning
Xi Lin, Hui-Ling Zhen, Zhenhua Li, Qingfu Zhang, Sam Kwong
Advances in Neural Information Processing Systems (NeurIPS) , 2019
pdf / arXiv / proceedings / code

Academic Service

Action Editor (aka Associate Editor): Transactions on Machine Learning Research (TMLR)
Conference Reviewer: ICML, ICLR, NeurIPS, AISTATS, GECCO, CEC, SSCI
Journal Reviewer: JMLR, TMLR, TEVC, TCYB, TNNLS, TAI, TETCI, NN, SWEVO, COR
Awards:
Expert Reviewer, TMLR 2023
Outstanding Reviewer, ICML 2021, ICML 2022
Highlighted Reviewer, ICLR 2022

This website's source code is adapted from Jon Barron's public academic website.