Chaoyang He (何朝阳) Ph.D. Student in Computer Science University of Southern California, Los Angeles, USA Team Manager and Staff Engineer at Tencent (2014-2018) Senior Software Engineer at Baidu (2012-2014) Email: chaoyang.he [at] usc [dot] edu me [at] chaoyanghe [dot] com

Chaoyang He is a Computer Science Ph.D. student focusing on Machine Learning at University of Southern California, Los Angeles, USA. Previously, he was an R&D Team Manager and Principal Engineer at Tencent (2014-2018), a Team Leader and Senior Software Engineer at Baidu (2012-2014), and a Software Engineer at Huawei (2011-2012).

Currently, his academic advisors are Professor Salman Avestimehr (USC, machine learning theory, distributed computing), Murali Annavaram (USC & Facebook, machine learning system, computer architecture), and Tong Zhang (HKUST, machine learning optimization)

He has a strong background in Internet industrial level computer science, including cloud computing architecture, machine learning, and data computing platform, distributed systems, mobile computing, and embedded operating system. He has more than three years of experience in Internet R&D management, leading a team with 10-20 software engineers and researchers to build commercial Internet products. The Internet Products that he worked for include Tencent Cloud , Tencent WeChat Automative / AI in Car (news report, a talk by CEO Pony Ma ), Tencent Games, Tencent Maps, Baidu Maps, and Huawei Smartphone.

His expertise lies in machine learning, deep learning, distributed systems, cloud computing and mobile computing. Currently, his primary research interest is machine learning algorithms, models and systems, especially Efficient and Automated Deep Learning:

• Learning Paradigms Towards Efficient DL: graph neural networks (GCNs), GAN/VAE, reinforcement learning, multi-task learning/transfer learning, meta-learning, unsupervised/semi-supervised Learning, etc.
• Efficient Neural Architecture Design: automated machine learning (AutoML), neural architecture search (NAS)
• Training-Efficient - accelerating the training speed under constrained or unlimited resource, including but not limited to decentralized learning, distributed learning, federated learning, on-device training, etc.
• HPO-Efficient: efficient and robust hyper-parameter tuning
• Inference-Efficient: speed up large scale model on-resource constrained devices (Mobile, AR/VR), model compression; high concurrency model serving on the cloud
• Data-Efficient: label and sample efficient learning, including but not limited to meta-learning, self-supervised learning, semi-supervised learning, unsupervised learning.
• Development-Efficient: distributed learning library, AutoML framework, model compression library.
• Efficient AI Applications: computer vision, natural language processing, and data mining (Transportation, Games, Finance, Health Care, etc.)
• Theory Towards Efficient DL: convex/non-convex optimization, information theory, distributed computing optimization
• Any efficient AI-related Mathematics and complex computer systems

Papers

• FedNAS: Federated Deep Learning via Neural Architecture Search
  Chaoyang He, Murali Annavaram, Salman Avestimehr
  Accepted to CVPR 2020 Workshop on Neural Architecture Search and Beyond for Representation Learning
[bib] [arXiv] [code] [video]
Keywords: AutoML, Neural Architecture Search, Federated Learning, Computer Vision


• Bipartite Graph Neural Networks for Efficient Node Representation Learning
  Chaoyang He^*, Tian Xie^*, Yu Rong, Wenbing Huang, Yanfang Li, Junzhou Huang, Xiang Ren, Cyrus Shahabi
  Preprint, 2020

        @article{he2019bipartite,
          title={Bipartite Graph Neural Networks for Efficient Node Representation Learning},
          author={He, Chaoyang and Xie, Tian and Rong, Yu and Huang, Wenbing and Li, Yanfang and Huang, Junzhou and Ren, Xiang and Shahabi, Cyrus},
          journal={arXiv preprint arXiv:1906.11994},
          year={2019}
        }
    

[bib] [arXiv]
Keywords: Graph Neural Networks, Self-supervised Learning, Adversarial Learning, Efficient Neural Architecture


• Central Server Free Federated Learning over Single-sided Trust Social Networks
  Chaoyang He, Conghui Tan, Hanlin Tang, Shuang Qiu, Ji Liu
  Preprint, 2020

        @article{he2019central,
          title={Central server free federated learning over single-sided trust social networks},
          author={He, Chaoyang and Tan, Conghui and Tang, Hanlin and Qiu, Shuang and Liu, Ji},
          journal={arXiv preprint arXiv:1910.04956},
          year={2019}
        }
    

[bib] [arXiv]
Keywords: Distributed Machine Learning, Convex Optimization, Federated Learning, Online Learning


• MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
  Chaoyang He^*, Haishan Ye^*, Li Shen, Tong Zhang
  To appear in CVPR 2020 (IEEE/CVF Conference on Computer Vision and Pattern Recognition 2020)

        @inproceedings{MiLeNAS,
          title={MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation},
          author={He, Chaoyang and Ye, Haishan and Shen, Li and Zhang, Tong},
          booktitle={Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
          year={2020},
        }
    

[bib] [arXiv] [video]
Keywords: Neural Architecture Search, AutoML, Machine Learning Optimization, Computer Vision.


• Advances and Open Problems in Federated Learning
  Peter Kairouz, H Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael GL d'Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adria Gascón, Badih Ghazi, Phillip B Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konečný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrede Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X Yu, Han Yu, Sen Zhao
  To appear in Foundations and Trends in Machine Learning (FnTML), 2019

        @article{kairouz2019advances,
          title={Advances and open problems in federated learning},
          author={Kairouz, Peter and McMahan, H Brendan and Avent, Brendan and Bellet, Aur{\'e}lien and Bennis, Mehdi and Bhagoji, Arjun Nitin and Bonawitz, Keith and Charles, Zachary and Cormode, Graham and Cummings, Rachel and others},
          journal={arXiv preprint arXiv:1912.04977},
          year={2019}
        }
    

[bib] [arxiv]
with Google AI, Seattle, WA, USA


• Collecting Indicators of Compromise from Unstructured Text of Cybersecurity Articles using Neural-Based Sequence Labelling
  Zi Long, Lianzhi Tan, Shengping Zhou, Chaoyang He, Xin Liu
  International Joint Conference on Neural Networks (IJCNN), 2019

        @inproceedings{long2019collecting,
          title={Collecting Indicators of Compromise from Unstructured Text of Cybersecurity Articles using Neural-Based Sequence Labelling},
          author={Long, Zi and Tan, Lianzhi and Zhou, Shengping and He, Chaoyang and Liu, Xin},
          booktitle={2019 International Joint Conference on Neural Networks (IJCNN)},
          pages={1--8},
          year={2019},
          organization={IEEE}
        }
    

[bib] [arxiv]
Keywords: Natural Language Processing, Attention-based Bi-LSTM


• ADMSv2: A Modern Architecture for Transportation Data Management and Analysis
  Chrysovalantis Anastasiou, Jianfa Lin, Chaoyang He, Yao-Yi Chiang, Cyrus Shahabi
  SIGSPATIAL Workshop 2019

        @inproceedings{anastasiou2019admsv2,
          title={ADMSv2: A Modern Architecture for Transportation Data Management and Analysis},
          author={Anastasiou, Chrysovalantis and Lin, Jianfa and He, Chaoyang and Chiang, Yao-Yi and Shahabi, Cyrus},
          booktitle={Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances on Resilient and Intelligent Cities},
          pages={25--28},
          year={2019}
        }
    

[bib] [paper]
Keywords: System Architecture Design, TensorFlow/PyTorch, Spark, HIVE, Node.JS, MongoDB

Technical Report

(If you are interested in the following topics, please email me to discuss the potential collaboration.)
• 2018 - Data-Driven Cloud Computing Platform and Machine Learning System for the Internet of Vehicles
• 2016 - The Large-Scale Distributed System and Real-Time Location Data Mining
• 2017 - TAI: An Intelligent Operating System and Open Platform
• 2016 - Speech Recognition System for Connected and Autonomous Driving Car
• 2016 - WeGameMap: Real World Map Rendering Engine for Location-Based Mobile Game
• 2015 - WeLink: a High-Performance Vehicle-Mobile Networking Library
• 2014 - TMAP: A System Framework for Mobile Maps and Navigation
• 2016 - Efficient Spatial Anti-Aliasing Rendering for Line Joins on Vector Maps
• 2014 - WeCross: a Mobile and Vehicle C/C++ Cross-Platform Library
• 2017 - A High Precision Private Car Trajectory Dataset and an Open Source Location Data Computing Platform
• 2017 - A Open Source High Reliable Location SDK for the Automotive Industry
• 2013 - The First Generation Mobile Navigation SDK Design in China
• 2012 - Map State Switching under Multi-trigger Condition Based on Finite State Machine Design Pattern
• 2012 - A General Downloader Engine for iOS/Android Platform
• 2012 - The Best Practice for Java Native Interface (JNI) Development on Android Operating Platform
• 2014 - Taxi-Calling Platform and the Open Source Code
• 2015 - A UX design of Bluetooth Steering Wheel Wireless Controller and the communication system design
• 2016 - Sliding Window Algorithm Template to Solve All the Leetcode Substring Search Problem.

Patents

• Method for recognizing semantics, device storage medium and electronic device
  Patent number: CN109933774A
• A kind of voice recognition processing method and device
  Patent number: CN107293294A
• The data-pushing of vehicle cloud platform, treating method and apparatus
  Patent number: CN108833489A
• Method and apparatus for playing instant message sound on vehicle-mounted terminal
  Patent number: CN105530171A
• Resource obtaining method, terminal and vehicle terminal
  Patent number: CN105610978A
• Information interaction method and vehicle terminal
  Patent number: CN105791395A
• A kind of application development method, device, equipment and development frame
  Patent number: CN107179916A
• The rendering method and device of map, storage medium, electronic device
  Patent number: CN109544658A
• Selective recording method after realizing break-in of dispatching console in digital cluster system
  Patent number: CN101969444A

• Tencent Outstanding Staff Award (selection ratio < 1%, led to a promotion as Team Manager), 2015-2016
• WeChat MyCar, Special Award for Innovation, Mercedes-Benz, Daimler Supplier Award 2016 (teamwork; I worked as the technical leader)
• Baidu LBS Group Star Awards (6 holders among 1000+ employees), 2013
• Huawei Golden Network Award in 2012
• Province-level Outstanding Undergraduate Thesis Awards, 2008
• The First Prize Scholarship for undergraduate students, 2007

• CSCI 567-Machine Learning, with Professor Victor Adamchik, Summer 2019
• CSCI 567-Machine Learning, with Professor Victor Adamchik, Fall 2019
• INF 552-Machine Learning for Data Science, with Professor Satish Kumar Thittamaranahalli, Spring 2020
  
  I documented an open and editable Teaching Statement at https://www.overleaf.com/6136771432bggvjvhshrkz, including my experience introduction, teaching philosophy, future plan, and some useful notes in the machine learning course. I will update it once I have more insights on teaching.

• Team manager at Tencent, led a SDE team including 15+ software engineers, 2015-2018
• Team leader at Baidu, led 11 software engineers, 2013-2014

• CSCI699-Advanced Topics in Deep Learning, Spring 2019
• CSCI699-Advanced Computer Vision, Fall 2019
• CSCI699-Machine Learning for Knowledge Extraction and Reasoning (a PhD-level NLP course), Spring 2019
• CSCI599-Deep Learning and its Applications, Spring 2019
• CSCI698 Practicum in Teaching Computer Science, Spring 2019
• CSCI698 Practicum in Teaching Computer Science, Spring 2020
• CSCI697-Seminar in Computer Science Research, Fall 2018
• CSCI697-Seminar in Computer Science Research, Fall 2019
• ENGR502x-Writing Skills for Engineering Ph.D. Students, Fall 2018
• ALI246-Intermediate Oral Communication for ITAs, Fall 2018