Computational modeling

Ternary Compression for Communication-Efficient Federated Learning

Learning over massive data stored in different locations is essential in many real-world applications. However, sharing data is full of …

Jinjin Xu, Wenli Du, Yaochu Jin, Wangli He, Ran Cheng

Reference Vector-Assisted Adaptive Model Management for Surrogate-Assisted Many-Objective Optimization

Acquisition functions for surrogate-assisted many-objective optimization require a delicate balance between convergence and diversity. …

Qiqi Liu, Ran Cheng, Yaochu Jin, Martin Heiderich, Tobias Rodemann

RL-CSL: A Combinatorial Optimization Method Using Reinforcement Learning and Contrastive Self-Supervised Learning

Reinforcement learning-based methods have shown great potential in solving combinatorial optimization problems. However, the related …

Zhongju Yuan, Genghui Li, Zhenkun Wang, Jianyong Sun, Ran Cheng

Surrogate-assisted Multiobjective Neural Architecture Search for Real-time Semantic Segmentation

The architectural advancements in deep neural networks have led to remarkable leap-forwards across a broad array of computer vision …

Zhichao Lu, Ran Cheng, Shihua Huang, Haoming Zhang, Changxiao Qiu, Fan Yang

Evolutionary Multiobjective Optimization Driven by Generative Adversarial Networks (GANs)

Recently, increasing works have been proposed to drive evolutionary algorithms using machine-learning models. Usually, the performance …

Cheng He, Shihua Huang, Ran Cheng, Kay Chen Tan, Yaochu Jin

Surrogate-Assisted Expensive Many-Objective Optimization by Model Fusion

Surrogate-assisted evolutionary algorithms have played an important role in expensive optimization where a small number of …

Cheng He, Ran Cheng, Yaochu Jin, Xin Yao

Surrogate-Assisted Cooperative Swarm Optimization of High-Dimensional Expensive Problems

Surrogate models have shown to be effective in assisting metaheuristic algorithms for solving computationally expensive complex …

Chaoli Sun, Yaochu Jin, Ran Cheng, Jinliang Ding, Jianchao Zeng