CV

Education

• Ph.D in Computer Science, Victoria University of Wellington, New Zealand, 2024
• M.S. in Electrical Engineering, Shenzhen University, China, 2020
• B.S. in Electrical Engineering, Shenzhen University, China, 2017

Work experience

• Postdoctoral Research Fellow, Victoria University of Wellington, 2024.06 - Present
• Research Assistant, Victoria University of Wellington, 2023.06 - 2024.06
• Algorithm Engineer, Huawei Technologies Co., Ltd., 2020.08 - 2020.11

Research Interests

• Neural Architecture Search
• Automated Machine Learning
• Evolutionary Deep Learning
• Multi-Objective Machine Learning
• Evolutionary Computation
• Model Compression
• Ensemble Learning

Publications

Activation features empowered: An efficient gradient-free proxy to zero-shot neural architecture search

J. Huang, B. Xue, Y. Sun, M. Zhang, and G. G. Yen, “Activation features empowered: An efficient gradient-free proxy to zero-shot neural architecture search,” Pattern Recognition, vol. 179, p. 113917, 2026.

EvoREP: Evolving Reliable Ensemble of Zero-Cost Proxies for Zero-Shot Neural Architecture Search

J. Huang, B. Xue, Y. Sun, M. Zhang, and G. G. Yen, “EvoREP: Evolving reliable ensemble of zero-cost proxies for zero-shot neural architecture search,” IEEE Transactions on Evolutionary Computation, pp. 1–15, 2025.

Lightweight Neural Architecture Search via Training-Free ZiCo-Block Evaluation

Y. Wang, J. Huang, and R. Jiao, “Lightweight neural architecture search via training-free ZiCo-Block evaluation,” in PRICAI 2025: Trends in Artificial Intelligence, Lecture Notes in Computer Science, vol. 16452. Singapore: Springer Nature Singapore, 2026, pp. 67–82.

Automated Design of Neural Networks for River Flow Prediction Using Weather Data

J. Huang, R. Chaput, B. Xue, I. Liu, R. Vennell, and M. Zhang, “Automated design of neural networks for river flow prediction using weather data,” in PRICAI 2025: Trends in Artificial Intelligence, Lecture Notes in Computer Science, vol. 16452. Singapore: Springer Nature Singapore, 2026, pp. 346–362.

Evolving Comprehensive Proxies for Zero-Shot Neural Architecture Search

Junhao Huang, Bing Xue, Yanan Sun, and Mengjie Zhang. 2025. Evolving Comprehensive Proxies for Zero-Shot Neural Architecture Search. In Genetic and Evolutionary Computation Conference (GECCO), July 14-18, 2025, Malaga, Spain. ACM, New York, NY, USA, 9 pages. https://doi.org/10.1145/3712256.3726315

Efficient Perturbation-Aware Distinguishing Score for Zero-Shot Neural Architecture Search

J. Huang, B. Xue, Y. Sun, M. Zhang, and G. G. Yen, “Efficient perturbation-aware distinguishing score for zero-shot neural architecture search,” Applied Soft Computing, vol. 182, p. 113447, 2025.

LightMix: Multi-Objective Search for Lightweight Mixed-Scale Convolutional Neural Networks

J. Huang, B. Xue, Y. Sun, M. Zhang, and G. G. Yen, “LightMix: Multi-objective search for lightweight mixed-scale convolutional neural networks,” IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 10, no. 2, pp. 1654–1668, 2026.

Automatic Design of Neural Networks with Multi-Scale Convolutions via Multi-Path Weight Sampling

J. Huang, B. Xue, Y. Sun, M. Zhang, and G. G. Yen, “Automatic design of neural networks with multi-scale convolutions via multi-path weight sampling,” Pattern Recognition, vol. 165, p. 111605, 2025.

Multi-Objective Evolutionary Search of Compact Convolutional Neural Networks with Training-Free Estimation

Split-Level Evolutionary Neural Architecture Search With Elite Weight Inheritance

J. Huang, B. Xue, Y. Sun, M. Zhang, and G. G. Yen, “Split-level evolutionary neural architecture search with elite weight inheritance,” IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 10, pp. 13 523–13 537, 2024.

EDE-NAS: An Eclectic Differential Evolution Approach to Single-Path Neural Architecture Search

J. Huang, B. Xue, Y. Sun, and M. Zhang, “EDE-NAS: An eclectic differential evolution approach to single-path neural architecture search,” in AI 2022: Advances in Artificial Intelligence, Lecture Notes in Computer Science, vol. 13728. Cham: Springer International Publishing, 2022, pp. 116–130.

Particle Swarm Optimization for Compact Neural Architecture Search for Image Classification

J. Huang, B. Xue, Y. Sun, M. Zhang, and G. G. Yen, “Particle swarm optimization for compact neural architecture search for image classification,” IEEE Transactions on Evolutionary Computation, vol. 27, no. 5, pp. 1298–1312, 2023.

A Flexible Variable-length Particle Swarm Optimization Approach to Convolutional Neural Network Architecture Design

J. Huang, B. Xue, Y. Sun, and M. Zhang, “A flexible variable-length particle swarm optimization approach to convolutional neural network architecture design,” in 2021 IEEE Congress on Evolutionary Computation (CEC), Kraków, Poland, 2021, pp. 934–941.

Joint Structure and Parameter Optimization of Multiobjective Sparse Neural Network

J. Huang, W. Sun, and L. Huang, “Joint structure and parameter optimization of multiobjective sparse neural network,” Neural Computation, vol. 33, no. 4, pp. 1113–1143, 2021.

Deep Neural Networks Compression Learning Based on Multiobjective Evolutionary Algorithms

J. Huang, W. Sun, and L. Huang, “Deep neural networks compression learning based on multiobjective evolutionary algorithms,” Neurocomputing, vol. 378, pp. 260–269, 2020.

Deep Compression with Low Rank and Sparse Integrated Decomposition

J. Huang, W. Sun, L. Huang, and S. Chen, “Deep compression with low rank and sparse integrated decomposition,” in 2019 IEEE 7th International Conference on Computer Science and Network Technology (ICCSNT), Dalian, China, 2019, pp. 289–292.

Compressing Fully Connected Layers using Kronecker Tensor Decomposition

S. Chen, W. Sun, L. Huang, X. Yang, and J. Huang, “Compressing fully connected layers using Kronecker tensor decomposition,” in 2019 IEEE 7th International Conference on Computer Science and Network Technology (ICCSNT), Dalian, China, 2019.

Talks

Teaching

Service and leadership