I am a Senior Research Scientist working in the conversational AI team in Facebook Reality Lab. My research focuses are machine learning and optimization. Particularly, my current research focus on 1. Federated Learning 2. online learning for Conversational AI agents.
I have also worked on optimization and machine learning problems inspired by Intelligent Transportation Systems applications (e.g online and temporal prediction, learning for discrete choice modeling).
E-mail: my firstname dot lastname At *mail.com, where * = g
I will be serving as program committee member in the 3rd NLP4ConvAI workshop in EMNLP 2021.
Our paper "Federated Learning with Buffered Asynchronous Aggregation" is accepted to FL-ICML 2021 workshop and oral presentation (top 15% submission). Please see Research page for details.
Convex Latent Effect Logit Model via Sparse and Low-rank Decomposition
Hongyuan Zhan, Kamesh Madduri, Venkataraman Shankar. arXiv preprint arXiv:2108.09859, 2021
Federated Learning with Buffered Asynchronous Aggregation (long version, under review)
John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Michael Rabbat, Mani Esmaeili Malek, and Dzmitry Huba.. arXiv preprint arXiv:2106.06639, 2021
Federated Learning with Buffered Asynchronous Aggregation (workshop version).
John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Michael Rabbat, Mani Esmaeili Malek, and Dzmitry Huba. In International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with International Conference on Machine Learning 2021 (FL-ICML’21), 2021
HIGHLIGHTS accepted for oral presentation, top 15% submission
Evaluating Lottery Tickets under Distributional Shifts.
Shrey Desai, Hongyuan Zhan, and Ahmed Aly. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 153–162, 2019
Consensus Ensemble System for Traffic Flow Prediction.
Hongyuan Zhan, Gabriel Gomes, Xiaoye S Li, Kamesh Madduri, Alex Sim, and Kesheng Wu. IEEE Transactions on Intelligent Transportation Systems, 19(12):3903–3914, 2018
HIGHLIGHTS Methods developed in this paper are used by the California Department of Transportation (CalTran) in the Connected Corridor project. Media coverages: 1, 2, 3
Efficient Online Hyperparameter Optimization for Kernel Ridge Regression with Applications to Traffic Time Series Prediction.
Hongyuan Zhan, Gabriel Gomes, Xiaoye S Li, Kamesh Madduri, and Kesheng Wu. arXiv preprint arXiv:1811.00620, 2018
Efficient Online Hyperparameter Learning for Traffic Flow Prediction.
Hongyuan Zhan, Gabriel Gomes, Xiaoye S Li, Kamesh Madduri, and Kesheng Wu. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pages 164–169. IEEE, 2018
Analyzing Community Structure in Networks.
Hongyuan Zhan and Kamesh Madduri. In 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pages 1540–1549. IEEE, 2017
Gsk: Graph Sparsification as a Knapsack Problem Formulation.
Hongyuan Zhan and Kamesh Madduri. In The Third SDM Workshop on Mining Networks and Graphs: A Big Data Analytic Challenge, pages 32–40, 2016
