Binghong Chen

PhD Student, ML@GT

binghong [AT] gatech.edu

Bio

I am a Ph.D. student in the Machine Learning Center at Georgia Tech (ML@GT) advised by Le Song and Chao Zhang. My research primarily focuses on developing deep learning models and methodologies for a wide spectrum of problems with discrete structures such as code optimization, drug design, retrosynthesis for molecules/polymers, SAT/SMT solving, theorem proving, neural symbolic reasoning, and path planning. My other interests include pre-training methods on text and graph data, such as BERT and contrastive learning.

Publications

Learning to Improve Code Efficiency

Binghong Chen, Daniel Tarlow, Kevin Swersky, Martin Maas, Pablo Heiber, Ashish Naik, Milad Hashemi, Parthasarathy Ranganathan

preprint

Deep learning driven biosynthetic pathways navigation for natural products with BioNavi-NP

Shuangjia Zheng, Tao Zeng, Chengtao Li, Binghong Chen, Connor W. Coley, Yuedong Yang, Ruibo Wu

Nature Communications 2022

Spanning Tree-based Graph Generation for Molecules

Sungsoo Ahn, Binghong Chen, Tianzhe Wang, Le Song

International Conference on Learning Representations (ICLR) 2022 spotlight

ProTo: Program-Guided Transformer for Program-Guided Tasks

Zelin Zhao, Karan Samel, Binghong Chen, Le Song

Conference on Neural Information Processing Systems (NeurIPS) 2021

Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning

Jiani Huang, Ziyang Li, Binghong Chen, Karan Samel, Xujie Si, Le Song, Mayur Naik

Conference on Neural Information Processing Systems (NeurIPS) 2021

ARBITRAR: User-Guided API Misuse Detection

Ziyang Li, Aravind Machiry, Binghong Chen, Ke Wang, Mayur Naik, Le Song

IEEE Symposium on Security and Privacy (IEEE S&P) 2021

Molecule Optimization by Explainable Evolution

Binghong Chen, Tianzhe Wang, Chengtao Li, Hanjun Dai, Le Song

International Conference on Learning Representations (ICLR) 2021

Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search

Binghong Chen, Chengtao Li, Hanjun Dai, Le Song

International Conference on Machine Learning (ICML) 2020

Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees

Binghong Chen, Bo Dai, Qinjie Lin, Guo Ye, Han Liu, Le Song

International Conference on Learning Representations (ICLR) 2020 spotlight

GLAD: Learning Sparse Graph Recovery

Harsh Shrivastava, Xinshi Chen, Binghong Chen, Guanghui Lan, Srinivas Aluru, Le Song

International Conference on Learning Representations (ICLR) 2020

Graph Contrastive Pre-training for Effective Theorem Reasoning

Zhaoyu Li, Binghong Chen, Xujie Si

Self-Supervised Learning for Reasoning and Perception Workshop (ICML) 2021 contributed talk

PolyRetro: Few-shot Polymer Retrosynthesis via Domain Adaptation

Binghong Chen, Chengtao Li, Hanjun Dai, Rampi Ramprasad, Le Song

preprint

Learning to Improve Code Efficiency

Binghong Chen, Daniel Tarlow, Kevin Swersky, Martin Maas, Pablo Heiber, Ashish Naik, Milad Hashemi, Parthasarathy Ranganathan

preprint

Deep learning driven biosynthetic pathways navigation for natural products with BioNavi-NP

Shuangjia Zheng, Tao Zeng, Chengtao Li, Binghong Chen, Connor W. Coley, Yuedong Yang, Ruibo Wu

Nature Communications 2022

Spanning Tree-based Graph Generation for Molecules

Sungsoo Ahn, Binghong Chen, Tianzhe Wang, Le Song

International Conference on Learning Representations (ICLR) 2022 spotlight

ProTo: Program-Guided Transformer for Program-Guided Tasks

Zelin Zhao, Karan Samel, Binghong Chen, Le Song

Conference on Neural Information Processing Systems (NeurIPS) 2021

Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning

Jiani Huang, Ziyang Li, Binghong Chen, Karan Samel, Xujie Si, Le Song, Mayur Naik

Conference on Neural Information Processing Systems (NeurIPS) 2021

ARBITRAR: User-Guided API Misuse Detection

Ziyang Li, Aravind Machiry, Binghong Chen, Ke Wang, Mayur Naik, Le Song

IEEE Symposium on Security and Privacy (IEEE S&P) 2021

Molecule Optimization by Explainable Evolution

Binghong Chen, Tianzhe Wang, Chengtao Li, Hanjun Dai, Le Song

International Conference on Learning Representations (ICLR) 2021

Speeding up Computational Morphogenesis with Online Neural Synthetic Gradients

Yuyu Zhang, Heng Chi, Binghong Chen, Tsz Ling Elaine T., Lucia M., Le Song, Glaucio H. P.

International Joint Conference on Neural Networks (IJCNN) 2021

Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search

Binghong Chen, Chengtao Li, Hanjun Dai, Le Song

International Conference on Machine Learning (ICML) 2020

Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees

Binghong Chen, Bo Dai, Qinjie Lin, Guo Ye, Han Liu, Le Song

International Conference on Learning Representations (ICLR) 2020 spotlight

GLAD: Learning Sparse Graph Recovery

Harsh Shrivastava, Xinshi Chen, Binghong Chen, Guanghui Lan, Srinivas Aluru, Le Song

International Conference on Learning Representations (ICLR) 2020

Learning Temporal Rules from Noisy Timeseries Data

Karan Samel, Zelin Zhao, Binghong Chen, Shuang Li, Dharmashankar Subramanian, Irfan Essa, Le Song

preprint

PolyRetro: Few-shot Polymer Retrosynthesis via Domain Adaptation

Binghong Chen, Chengtao Li, Hanjun Dai, Rampi Ramprasad, Le Song

preprint

Differentiable End-to-End Program Executor for Sample and Computationally Efficient VQA

Karan Samel, Zelin Zhao, Kuan Wang, Robin Luo, Binghong Chen, Le Song

preprint

Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning

Jiani Huang, Ziyang Li, Binghong Chen, Karan Samel, Xujie Si, Le Song, Mayur Naik

Advances in Programming Languages and Neurosymbolic Systems Workshop (NeurIPS) 2021

Large Scale Coordination Transfer for Cooperative Multi-Agent Reinforcement Learning

Ethan Wang, Binghong Chen, Le Song

Deep Reinforcement Learning Workshop (NeurIPS) 2021

Graph Contrastive Pre-training for Effective Theorem Reasoning

Zhaoyu Li, Binghong Chen, Xujie Si

Self-Supervised Learning for Reasoning and Perception Workshop (ICML) 2021 contributed talk

Learning Retrosynthetic Planning with Chemical Reasoning

Binghong Chen, Chengtao Li, Hanjun Dai, Le Song

Bridge Between Perception and Reasoning: GNN and Beyond Workshop (ICML) 2020 spotlight

Learning Neural Retrosynthetic Planning

Binghong Chen, Chengtao Li, Hanjun Dai, Le Song

AI Powered Drug Discovery and Manufacturing Conference (AIDM) 2020

Learning to Plan via Neural Exploration-Exploitation Trees

Binghong Chen, Bo Dai, Le Song

Learning Transferable Skills Workshop (NeurIPS) 2019

Selected Projects

Learning Retrosynthetic Planning
Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
Neurally-guided Path Planning
Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees

Vitæ

Full Resume in PDF.

  • Amazon Summer 2022
    Applied Scientist Intern
    Amazon Search Science & AI
  • Google Spring 2022
    Research Intern
  • JPMorgan Chase Fall 2021
    Machine Learning Research Intern
    Machine Learning Center of Excellence
  • Google Summer 2021
    Research Intern
    Worked with Milad Hashemi, Kevin Swersky, and Danny Tarlow
  • Machine Learning Group @ GT 2017 - now
    Research Assistant
    Advised by Le Song
  • Georgia Institute of Technology 2017 - now
    Ph.D. Student
    Machine Learning Center
  • Carnegie Mellon University Summer 2016
    Research Intern
    Advised by Eric P. Xing
  • Tsinghua SAIL Group 2014-2017
    Undergraduate Research Assistant
    Advised by Jun Zhu
  • Tsinghua University 2013 - 2017
    B.Eng. Student
    Department of Computer Science

Services

Program committee (reviewer):
NeurIPS, ICML, ICLR, AISTATS, IJCAI, AAAI, SIGKDD, Nature Machine Intelligence

Awards

  • Outstanding Graduate, Tsinghua University, 2017
  • National Scholarship (<2%), Ministry of Education of China, 2016
  • Scholarship of Academic Excellence, Tsinghua University, 2015/2014
  • Silver Medal (<0.02%), China Mathematics Olympiad, 2013

Acknowledgement

This website was built with jekyll based on a template by Martin Saveski.