Haoming Jiang

Email: jianghm@gatech.edu
Github: HMJiangGatech

About Me

I am an applied research scientist at Amazon Search (A9.com). Before I joined Amazon, I obtained my Ph.D. degree in Machine Learning from the School of Industrial and Systems Engineering (ISyE) at Georgia Tech. I spent wonderful years with Prof. Tuo Zhao in the FLASH (Foundations of LeArning Systems for alcHemy) research group. I received my B.S. degree in Computer Science and Mathematics from the School of the Gifted Young at University of Science and Technology of China (USTC).

My research focuses on deep learning, adversarial machine learning, natural language processing, and open-source software for data analysis.

Professional Experience

  • Applied Scientist, Amazon, 2021-present

  • Research Intern, Amazon, 2020 Fall

  • Research Intern, Google AI, 2020 Summer

  • Research Intern, Microsoft, 2019 Summer

Education

  • Ph.D. in Machine Learning, Georgia Institue of Technology, ISyE, 2017-2021

  • B.S. in Mathematics and Computer Science, University of Science and Technology of China, ScGY, 2013-2017

Research

Preprints And Working Papers

  • Boosting Pathwise Coordiante Optimization: Sequential Screening and Proximal Subsampled Newton Subroutine 2018
    Haoming Jiang, Xingguo Li, Jason Ge, Mengdi Wang, Mingyi Hong and Tuo Zhao [Code]

  • Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach 2021
    Haoming Jiang, Bo Dai, Mengjiao Yang, Tuo Zhao and Wei Wei [arXiv]

Publications

  • Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data 2021
    Haoming Jiang, Danqing Zhang, Tianyu Cao, Bing Yin and Tuo Zhao
    Annual Meeting of the Association for Computational Linguistics (ACL), 2021

  • Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization 2021
    Chen Liang, Simiao Zuo, Minshuo Chen, Haoming Jiang, Xiaodong Liu, Pengcheng He, Tuo Zhao and Weizhu Chen [arXiv]
    Annual Meeting of the Association for Computational Linguistics (ACL), 2021

  • Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach 2021
    Yue Yu, Simiao Zuo, Haoming Jiang, Wendi Ren, Tuo Zhao and Chao Zhang [arXiv]
    Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2021

  • Learning to Defense by Learning to Attack 2021
    Zhehui Chen*, Haoming Jiang*, Yuyang Shi, Bo Dai, and Tuo Zhao (* Equal Contribution) [arXiv]
    The 24th International Conference on Artificial Intelligence and Statistics (AISTATS), 2021

  • Calibrated Fine-Tuning for Pre-trained Language Models via Manifold Smoothing 2020
    Lingkai Kong, Haoming Jiang, Yuchen Zhuang, Jie Lyu, Tuo Zhao and Chao Zhang [arXiv]
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020

  • Deep Reinforcement Learning with Smooth Policy 2020
    Qianli Shen, Yan Li, Haoming Jiang, Zhaoran Wang, Tuo Zhao [arXiv]
    International Conference on Machine Learning (ICML), 2020

  • Transformer Hawkes Process 2020
    Simiao Zuo, Haoming Jiang, Zichong Li, Tuo Zhao, Hongyuan Zha [arXiv]
    International Conference on Machine Learning (ICML), 2020

  • BOND: Bert-Assisted Open-Domain Named Entity Recognition with Distant Supervision 2020
    Chen Liang*, Yue Yu*, Haoming Jiang*, Siawpeng Er, Ruijia Wang, Tuo Zhao and Chao Zhang (* Equal Contribution) [arXiv] [Code]
    The 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2020

  • SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization 2020
    Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao and Tuo Zhao [arXiv] [Code]
    Annual Conference of the Association for Computational Linguistics (ACL), 2020
    News (2019/12/05): Rank #1 on GLUE

  • Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing 2020
    Haoming Jiang, Chen Liang, Chong Wang and Tuo Zhao [arXiv] [Code]
    Annual Conference of the Association for Computational Linguistics (ACL), 2020

  • On the Variance of the Adaptive Learning Rate and Beyond 2020
    Liyuan Liu, Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao and Jiawei Han [arXiv] [Code]
    International Conference on Learning Representations (ICLR), 2020

  • Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds 2019
    Minshuo Chen, Haoming Jiang, Wenjing Liao and Tuo Zhao [arXiv]
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2019

  • Meta Learning with Relational Information for Short Sequences 2019
    Yujia Xie, Haoming Jiang, Feng Liu, Tuo Zhao and Hongyuan Zha [arXiv]
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2019

  • On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don't Worry About Its Nonsmooth Loss Function 2019
    Xingguo Li, Haoming Jiang, Jarvis Haupt, Raman Arora, Han Liu, Mingyi Hong and Tuo Zhao [arXiv] [Code]
    Conference on Uncertainty in Artificial Intelligence (UAI), 2019

  • On Scalable and Efficient Computation of Large Scale Optimal Transport 2019
    Yujia Xie, Minshuo Chen, Haoming Jiang, Tuo Zhao, Hongyuan Zha [arXiv] [Code]
    International Conference on Machine Learning (ICML), 2019

  • On Computation and Generalization of Generative Adversarial Networks under Spectrum Control 2019
    Haoming Jiang, Zhehui Chen, Minshuo Chen, Feng Liu, Dingding Wang, Tuo Zhao [arXiv] [Code]
    International Conference on Learning Representations (ICLR), 2019

  • Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python 2019
    Jason Ge*, Xingguo Li*, Haoming Jiang, Han Liu, Tong Zhang, Mengdi Wang and Tuo Zhao (*Equal Contribution) [PDF] [R Package] [Python Package]
    Journal of Machine Learning Research (JMLR), 2019

  • Contextual Text Denoising with Masked Language Model 2019
    Yifu Sun, Haoming Jiang [arXiv]
    Conference on Empirical Methods in Natural Language Processing (EMNLP), Workshop W-NUT, 2019

  • Designing Deployable 3D Scissor Structures with Ball-and-Socket Joints 2018
    Xuejin Chen, Haoming Jiang, Tingting Xuan, Lihan Huang, Ligang Liu [PDF]
    Computer Animation & Virtual Worlds (CAVW), 2018

  • Scissor-based 3D deployable contour 2017
    Haoming Jiang, Xuejin Chen, Tingting Xuan, Lihan Huang, Ligang Liu [PDF]
    International Conference on Virtual Reality and Visualization (ICVRV), 2017

Projects

Software

  • Arxiv Viewer: Checkout the webapp for daily arxiv papers: Arxiv Viewer

  • PICASSO: PathwIse CalibrAted Sparse Shooting algOrithm [R Package] [Python Package]

  • HUGE: High-Dimensional Undirected Graph Estimation [R Package]

  • SAM: Sparse Additive Modelling [R Package]

  • ESMOTE: Efficient Synthetic Minority Over-sampling Technique [R Package]

  • Setup Toolkits: A quick setup toolkit for vim,tmux,zsh on linux server [zip]

  • FlashPythonToolbox: A few ready-to use python tools for machine learning [Github]

Others

MISC

Notes

T5, Small BERT, MTDA, Distributed Optimization, Introduction to Data Mining ( 2 3 4 5 6 7 8 9 10 ), Social Media Mining ( Link Chp5 )