Haoyu Geng

Haoyu Geng

Ph.D. candidate

Shanghai Jiao Tong University

Haoyu Geng (耿 皓宇)

I am a PhD candidate in computer science at Shanghai Jiao Tong University (SJTU), supervised by Prof. Junchi Yan. Prior to this, I earned bachelor degree from IEEE Honor Class in SJTU, with major in Computer Science.

My research interests lie in theory and applications of graph learning and combinatorial optimization. (1) In graph learning, I aspire to develop novel algorithms in graph signal processing and graph neural networks with applications to recommender systems, urban computing, etc. (2) In combinatorial optimization (CO), I wish to explore end-to-end systems for the interplay of areas in machine learning and operational research (ML4CO).

I am always open for discussion and potential collaborations and please feel free to contact me via email: genghaoyu98 at sjtu dot edu dot cn

What's New
  • Two papers are accepted by KDD 2023!
  • Our EasyDGL preprint is available on arXiv and code is also available!
  • One paper on graph signal sampling is accepted by ICLR 2023!

Academic Services: I serve as Reviewer for NeurIPS 2023, ICLR 2024, LOG 2023, ICML 2024, IJCAI 2024

Interests

  • Graph Learning
  • Combinatorial Optimization

Education

  • Ph.D. in Computer Science, 2020-Current

    Shanghai Jiao Tong University

  • BSc in Computer Science, 2016-2020

    Shanghai Jiao Tong University

Recent Publications

Quickly discover relevant content by filtering publications.
Rethinking and Benchmarking Predict-then-Optimize Paradigm for Combinatorial Optimization Problems
Haoyu Geng, Hang Ruan, Runzhong Wang, Yang Li, Yang Wang, Lei Chen, Junchi Yan
PDF Arxiv
Pyramid Graph Neural Network: a Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations
Haoyu Geng, Chao Chen, Yixuan He, Gang Zeng, Zhaobing Han, Hua Chai, Junchi Yan, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023)
Code Poster Slides DOI ACM DL
GAL-VNE: Solving the VNE Problem with Global Reinforcement Learning and Local One-Shot Neural Prediction
Haoyu Geng, Runzhong Wang, Fei Wu, Junchi Yan, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023)
Code Poster Slides DOI ACM DL
Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution
Chao Chen, Haoyu Geng, Gang Zeng, Zhaobing Han, Hua Chai, Xiaokang Yang, Junchi Yan, International Conference on Learning Representations (ICLR 2023)
PDF Code OpenReview
EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning
Chao Chen, Haoyu Geng, Nianzu Yang, Xiaokang Yang, Junchi Yan
PDF Code Arxiv
HMES: A Scalable Human Mobility and Epidemic Simulation System with Fast Intervention Modeling
Haoyu Geng, Guanjie Zheng, Zhengqing Han, Hua Wei, Zhenhui Li, IEEE International Conference on Ubiquitous Intelligence and Computing (UIC 2022)
PDF Code Slides IEEE Xplore
Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
Chao Chen, Haoyu Geng, Nianzu Yang, Junchi Yan, Daiyue Xue, Jianping Yu, Xiaokang Yang, International Conference on Machine Learning (ICML 2021)
PDF Code Poster Slides MLR Press
Gated Sequential Recommendation System with Social and Textual Information under Dynamic Contexts
Haoyu Geng, Shuodian Yu, Xiaofeng Gao, International Conference on Database Systems for Advanced Applications (DASFAA 2021)
PDF Slides Springer

Projects

Awesome Machine Learning for Combinatorial Optimization Resources

A list of resources that utilize machine learning technologies to solve combinatorial optimization problems.

Talks

Application and practice of graph learning in management

Jun 7, 2023 13:00 — Jun 7, 2030 15:00
Link

Experience

 
 
 
 
 

Algorithm Intern

Didi

Dec 2021 – Aug 2022 Beijing
  • Deployed graph learning algorithms for Estimated Time of Arrival (ETA) in ride-hailing services.
 
 
 
 
 

Algorithm Intern

Meituan

May 2021 – Aug 2021 Beijing
  • Deployed Continuous-time attention on Meituan Recommendations with temporal point process
  • Our program Won 2020-2021 Best Research Collaboration Award at Meituan

Contact