Ma Jiale (麻家乐)

About

I am now a first-year PhD student majoring in Computer Science at School of Artificial Intelligence from Shanghai Jiao Tong University (SJTU), where I am fortunate to be supervised by Prof. Junchi Yan. I achieved the Bachelor degree from School of Computer Science at SJTU, and transitioned directly to the current PhD program. My research interests lie in machine learning, especially deep generative models and combinatorial optimization on graphs.

Academic Performance

Undergraduate period:

GPA: 90.81/100 (or 3.93/4.3), Rank: 7/73 (top 9.6%)
Courses: 67.14% above A, 28.6% above A+

Postgraduate period:

Due to just starting school in the first year, there are currently no grades

Selected Awards

Undergraduate National Scholarship (top 0.2% in the nation)
Outstanding Graduate of Shanghai (top 3%)
First-Class Cybersecurity Scholarship (top 10%)
1st-Class Academic Excellence Scholarship (top 1%)
Merit Student of Shanghai Jiao Tong University
Merit League Member of Shanghai Jiao Tong University

Selected Projects

I am systematically building a foundational framework for ML4CO with a collection of resources that complement each other in a cohesive manner.

Awesome-ML4CO, a curated collection of literature in the ML4CO field, organized to support researchers in accessing both foundational and recent developments.
ML4CO-Kit, a general-purpose toolkit that provides implementations of common algorithms used in ML4CO, along with basic training frameworks, traditional solvers and data generation tools. It aims to simplify the implementation of key techniques and offer a solid base for developing machine learning models for COPs.
ML4TSPBench: a benchmark focusing on exploring the TSP for representativeness. It advances a unified modular streamline incorporating existing tens of technologies in both learning and search for transparent ablation, aiming to reassess the role of learning and to discern which parts of existing techniques are genuinely beneficial and which are not. It offers a deep dive into various methodology designs, enabling comparisons and the development of specialized algorithms.
ML4CO-Bench-101: a benchmark that categorizes neural combinatorial optimization (NCO) solvers by solving paradigms, model designs, and learning strategies. It evaluates applicability and generalization of different NCO approaches across a broad range of combinatorial optimization problems to uncover universal insights that can be transferred across various domains of ML4CO.

selected publications

NeurIPS

ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs

Jiale Ma, Wenzheng Pan, Yang Li, and 1 more author

In Advances in Neural Information Processing Systems, 2025

Bib HTML PDF

@inproceedings{ma2025mlcobench,
  title = {ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs},
  author = {Ma, Jiale and Pan, Wenzheng and Li, Yang and Yan, Junchi},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2025}
}

ICML

COExpander: Adaptive Solution Expansion for Combinatorial Optimization

Jiale Ma, Wenzheng Pan, Yang Li, and 1 more author

In International Conference on Machine Learning, 2025

Bib HTML PDF

@inproceedings{macoexpander,
  title = {COExpander: Adaptive Solution Expansion for Combinatorial Optimization},
  author = {Ma, Jiale and Pan, Wenzheng and Li, Yang and Yan, Junchi},
  booktitle = {International Conference on Machine Learning},
  year = {2025}
}

ICML

Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning

Yang Li, Jiale Ma, Yebin Yang, and 3 more authors

In International Conference on Machine Learning, 2025

Bib HTML PDF

@inproceedings{ligenerative,
  title = {Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning},
  author = {Li, Yang and Ma, Jiale and Yang, Yebin and Wu, Qitian and Zha, Hongyuan and Yan, Junchi},
  booktitle = {International Conference on Machine Learning},
  year = {2025}
}

ICLR

ML4TSPBench: Streamlining the Design Space of ML4TSP Suggests Principles for Learning and Search

Yang Li, Jiale Ma, Wenzheng Pan, and 4 more authors

In International Conference on Learning Representations, 2025

Bib HTML PDF

@inproceedings{li2025ml4tsp,
  title = {ML4TSPBench: Streamlining the Design Space of ML4TSP Suggests Principles for Learning and Search},
  author = {Li, Yang and Ma, Jiale and Pan, Wenzheng and Wang, Runzhong and Geng, Haoyu and Yang, Nianzu and Yan, Junchi},
  booktitle = {International Conference on Learning Representations},
  year = {2025}
}

ICLR

UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP

Wenzheng Pan, Hao Xiong, Jiale Ma, and 3 more authors

In International Conference on Learning Representations, 2025

Bib HTML PDF

@inproceedings{pan2025unico,
  title = {UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP},
  author = {Pan, Wenzheng and Xiong, Hao and Ma, Jiale and Zhao, Wentao and Li, Yang and Yan, Junchi},
  booktitle = {International Conference on Learning Representations},
  year = {2025}
}

JMLR

Pygmtools: A Python Graph Matching Toolkit

Runzhong Wang, Ziao Guo, Wenzheng Pan, and 10 more authors

Journal of Machine Learning Research, 2024

Bib HTML PDF

@article{wang2024pygm,
  title = {Pygmtools: A Python Graph Matching Toolkit},
  author = {Wang, Runzhong and Guo, Ziao and Pan, Wenzheng and Ma, Jiale and Zhang, Yikai and Yang, Nan and Liu, Qi and Wei, Longxuan and Zhang, Hanxue and Liu, Chang and Jiang, Zetian and Yang, Xiaokang and Yan, Junchi},
  journal = {Journal of Machine Learning Research},
  year = {2024}
}