Mozhi Zhang (张墨之)

I am a Ph.D. candidate in Computer Science at the University of Maryland. My advisor is Jordan Boyd-Graber. I am also a member of CLIP lab.

My research focuses on building natural language processing models from limited data. This includes human-in-the-loop machine learning, transferring knowledge from other languages/domains, learning from noisy data, and understanding the inductive bias of deep learning.

During my PhD, I visited New York University (hosted by Kyunghyun Cho) and interned at Microsoft Research. I completed my B.S. and M.S.E. at the Johns Hopkins University, where I worked with Jason Eisner and David Yarowsky.

Selected Publications

* = equal contribution

How Does a Neural Network's Architecture Impact Its Robustness to Noisy Labels?
Jingling Li, Mozhi Zhang, Keyulu Xu, John P. Dickerson, Jimmy Ba
NeurIPS 2021
arxiv bibtex

A Dataset and Baselines for Multilingual Reply Suggestion
Mozhi Zhang, Wei Wang, Budhaditya Deb, Guoqing Zheng, Milad Shokouhi, Ahmed Hassan Awadallah
ACL 2021
arxiv bibtex data code

Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Keyulu Xu, Mozhi Zhang, Stefanie Jegelka, Kenji Kawaguchi
ICML 2021
arxiv bibtex

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Keyulu Xu, Mozhi Zhang, Jingling Li, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
ICLR 2021 (Oral)
arxiv bibtex code

Interactive Refinement of Cross-Lingual Word Embeddings
Michelle Yuan*, Mozhi Zhang*, Benjamin Van Durme, Leah Findlater, Jordan Boyd-Graber
EMNLP 2020
arxiv bibtex code video

Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries
Mozhi Zhang*, Yoshinari Fujinuma*, Michael J. Paul, Jordan Boyd-Graber
ACL 2020
arxiv bibtex code video

What Can Neural Networks Reason About?
Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
ICLR 2020 (Spotlight)
arxiv bibtex code

Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification
Mozhi Zhang, Yoshinari Fujinuma, Jordan Boyd-Graber
AAAI 2020
arxiv bibtex

Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
Mozhi Zhang, Keyulu Xu, Ken-ichi Kawarabayashi, Stefanie Jegelka, Jordan Boyd-Graber
ACL 2019
arxiv bibtex code