Zaid Khan

I’m a 2nd-year PhD student in machine learning at Northeastern University, advised by Dr. Yun Raymond Fu. My research interests are in trustworthy machine learning and multimodal learning. I’m currently working on two projects: sentiment understanding through better multimodal representations and robust learning on noisy, long-tailed data via predictive uncertainty.

Before starting my PhD, I spent ~3 years at two high growth startups (Roadie, Intelligent Flying Machines) as a software engineer, where I led efforts to scale data infrastructure to match growth, and worked on a range of challenging problems, including embedded deep learning, fault-tolerant distributed systems, realtime adaptive pricing, and data pipelines.

Outside of research, I lift weights, read (here’s my goodreads profile), watch mixed martial arts, think about whether probability is real, and cut down trees on RuneScape.

news

Jul 4, 2021 Our paper “Exploiting BERT for Multimodal Target Sentiment Classification Through Input Space Translation” was accepted into MM’ 21! (27.9% acceptance rate).
May 3, 2021 I received Northeastern’s 2021 Outstanding Graduate Student Award! 🎉
Feb 22, 2021 Our paper “One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision” was mentioned in News @ Northeastern.

selected publications

  1. ACM MM
    Exploiting BERT for Multimodal Target Sentiment Classification Through Input Space Translation
    Khan, Zaid, and Fu, Yun
    In ACM Conference on Multimedia 2021
  2. ACM FAccT
    One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision
    Khan, Zaid, and Fu, Yun
    In ACM Conference on Fairness, Accountability, and Transparency 2021