Avatar

Tong Jian

Email: jiant1170@gmail.com

Biography

I am a Research Scientist at Meta. My research interests broadly lie in the fields of deep learning security, recommendation systems, neural network compression, continual learning, and applied machine learning.

I received my PhD degree in Machine Learning at SPIRAL Group from Northeastern University, advised by Prof. Straitis Ioannidis. I also collaborated with Prof. Jennifer G. Dy and Prof. Yanzhi Wang on model compression and Prof. Kaushik Roy Chowdhury on applied machine learning to wireless communication.

I received my B.Eng. (2016) in Electrical Engineering from Xi'an Jiaotong University, enrolled in the Honors Youth Program.

I interned at Amazon as Applied Scientist in 2021 and Bell Labs, Nokia as Researcher in 2020.

Research

  • Model Compression
  • Recommendation Systems
  • Adversarial Robustness and Continuel (Lifelong) Learning
  • Deep learning applications in computer vision, wireless communications, etc.

    • News

  • 2022.09: One paper is accepted by NeurIPS 2022.
  • 2022.08: One paper is accepted by ICDM 2022.
  • 2022.08: Defense my PhD and graduate from Northeastern University, Good bye Boston.
  • 2022.04: One paper is accepted by IEEE TVT.
  • 2022.01: One paper is accepted by IEEE Trans. on Multimedia.
  • 2021.09: One paper is accepted by NeurIPS 2021.
  • 2021.06: Start my internship at Amazon, Seattle, WA as Applied Scientist.
  • 2021.03: One paper is accepted by IEEE TMC 2021.
  • 2020.09: One paper is accepted by ICDM 2020.
  • 2020.05: Receive the Outstanding Graduate Research Award from College of Engineering, NEU.
  • 2020.05: Start my internship at Bell Labs, Nokia, San Jose, CA.
  • 2020.04: One paper is accepted by INFOCOM 2020.
  • 2019.09: One paper is accepted by DySPAN 2019 as Best Paper.
  • 2018.09: Begin my new journey at Northeastern University, Boston, MA.

    • Experiences

    Sep 2018 - Aug 2022, Northeastern University

    Research assistant at SPIRAL Group

    June 2021 - Sep 2021, Amazon

    Applied Scientist Intern on Product Recommendation

    June 2020 - Aug 2020, Bell Labs

    Nokia, Research Intern on Applied Machine Learning to Wireless Communication

    Sep 2010 - May 2016, Xi’an Jiaotong University

    student enrolled in the Honors Youth Program (also known as Special Class for the Gifted Young)

    Selected Publications

    Google Scholar for all publications.

    Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness.

    Zifeng Wang*, Tong Jian*, Aria Masoomi, Stratis Ioannidis, Jennifer Dy

    Neural Information Processing Systems (NeurIPS), 2021.

    We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier, both theoretically and empirically.

    Radio Frequency Fingerprinting on the Edge.

    Tong Jian, Yifan Gong, Zheng Zhan, Runbin Shi, Nasim Soltani, Zifeng Wang, Jennifer G. Dy, Kaushik Roy Chowdhury, Yanzhi Wang, Stratis Ioannidis

    IEEE Transactions on Mobile Computing (IEEE TMC), 2021.

    We propose a deep learning solution for radio frequency fingerprinting deployments at resource-constrained edge devices.

    Learn-Prune-Share for Lifelong Learning.

    Zifeng Wang*, Tong Jian*, Kaushik Chowdhury, Yanzhi Wang, Jennifer Dy, Stratis Ioannidis

    International Conference on Data Mining (ICDM), 2020.

    We propose a learn-prune-share (LPS) algorithm which addresses the challenges of catastrophic forgetting, parsimony, and knowledge reuse simultaneously.

    Finding a ‘new’ needle in the haystack: Unseen radio detection in large populations using deep learning.

    Andrey Gritsenko*, Zifeng Wang*, Tong Jian, Jennifer Dy, Kaushik Chowdhury, Stratis Ioannidis

    IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), 2019.
    Best papar award [news]

    We propose a novel approach that facilitates new class detection without retraining a neural network, and perform extensive analysis of the proposed model both in terms of model parameters and real-world datasets.

    Awards

    Outstanding Graduate Research Award, Northeastern University. 2020.

    Awarded to students with exemplary record in the laboratory and the significant accomplishments in furthering research and scholarship.

    Best Paper Award, DySPAN 2019

    Dean's Fellowship, Northeastern University, 2018

    Highest honor awarded to new PhD students for out standing academic background.

    Academic Service

    Reviewer: NeurIPS, ICML, ICLR, AAAI, ICDM, SDM