Zhiyuan YAO

About

I am a research software engineer at Cisco Meraki. My responsibility consists of:

  • Conducting quantitative research based on a vast amount of telemetry data collected from data centers and millions of active networks worldwide.
  • Applying cutting-edge algorithms to a wide range of networking problems.
  • Deploying models and solutions in real-world distributed systems under various constraints (e.g. low latency, high throughput).

I recently completed my PhD degree in Computer Networking, which I pursued jointly between École Polytechnique’s networking team and Cisco Systems Paris Innovation and Research Lab (PIRL), advised by Thomas Clausen and Mark Townsley. My research interests include data-center networks, load-balancing, high-performance networking stacks, machine learning, reinforcement learning, and their applications in computer networking.

Before starting my PhD, I obtained a MSc&T in Internet-of-Things from École Polytechnique in 2019, and a BEng in Computational and Applied Methametics from Harbin Institut of Technology in 2017.

Contributions

Publications

My publication records can be found in my ORCID profile.

  • Zhiyuan Yao, and Zihan Ding. “Learning Distributed and Fair Policies for Network Load Balancing as Markov Potentia Game.”. In 36th Conference on Neural Information Processing Systems (NeurIPS’22). 2022. {pdf}

  • Zhiyuan Yao, Yoann Desmouceaux, Juan-Antonio Cordero-Fuertes, Mark Townsley, and Thomas Clausen. “Aquarius-Enable Fast, Scalable, Data-Driven Service Management in the Cloud.” IEEE Transactions on Network and Service Management (TNSM). 2022. {pdf, doi}

  • [Best Paper Award] Zhiyuan Yao, Yoann Desmouceaux, Juan Antonio Cordero Fuertes, Mark Townsley, and Thomas Heide Clausen. “Efficient Data-Driven Network Functions.” In 30th International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS’22). 2022. {pdf}

  • Zhiyuan Yao, Zihan Ding, and Thomas Clausen. “Multi-agent reinforcement learning for network load balancing in data center.” In 31st ACM International Conference on Information and Knowledge Management (CIKM’22). 2022. {pdf, doi}

  • Zhiyuan Yao, Yoann Desmouceaux, Juan-Antonio Cordero-Fuertes, Mark Townsley, and Thomas Clausen. “HLB: Toward Load-Aware Load Balancing.” IEEE/ACM Transactions on Networking (TON). 2022. {pdf, doi, blog}

  • Zhiyuan Yao, Yoann Desmouceaux, Mark Townsley, and Thomas Heide Clausen. “Towards Intelligent Load Balancing in Data Centers.” In 5th Workshop on Machine Learning for Systems at 35th Conference on Neural Information Processing Systems (NeurIPS’21). 2021. {pdf, blog}

  • Zhiyuan Yao, Zihan Ding, and Thomas Heide Clausen. “Reinforced Workload Distribution Fairness.” In 5th Workshop on Machine Learning for Systems at 35th Conference on Neural Information Processing Systems (NeurIPS’21). 2021. {pdf, blog}

  • Carmine Rizzi, Zhiyuan Yao, Yoann Desmouceaux, Mark Townsley, and Thomas Clausen. “Charon: Load-Aware Load-Balancing in P4.” In 1st Joint International Workshop on Network Programmability & Automation (NetPA) at 17th International Conference on Network and Service Management (CNSM’21). 2021. {pdf, doi, blog}

  • Yao Zhao, Sophine Zhang, and Zhiyuan Yao. “A Hybrid Approach for Smart Alert Generation” In 3rd IEEE International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME’23). 2023.

  • Mengoli, Emanuele, Zhiyuan Yao, Wutao Wei, and Thomas Clausen. “Develop End-to-End Anomaly Detection System.” In 2023 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 1370-1379. IEEE, 2023. {pdf, doi}

Teaching

  • Sécurité des Systèmes d’Information, Teaching Assistant, École Polytechnique, 2022
  • INF473X - Modal d’Informatique - Cybersecurity - The Hacking Xperience, Teaching Assistant, École Polytechnique, 2019-2022
  • INF557 Network Security, Teaching Assistant, École Polytechnique, 2019-2022
  • Advanced Control, Teaching Assistant, Technical University of Munich (TUM), 2016

Contact

Zhiyuan YAO
18 Rue Washinton
Tel: +33 (0)1 58 04 68 59
Email: {firstname}[dot]{surname}[at]polytechnique[dot]edu