195 citations · 451 across the 14 of their papers we have counts for
7 papers · 1 filter
Adversarial Support Alignment
Shangyuan Tong, Timur Garipov, Yang Zhang +2
We study the problem of aligning the supports of distributions. Compared to the existing work on distribution alignment, support alignment does not require the densities to be matc…
Understanding Interlocking Dynamics of Cooperative Rationalization
Mo Yu, Yang Zhang, Shiyu Chang +1
Selective rationalization explains the prediction of complex neural networks by finding a small subset of the input that is sufficient to predict the neural model output. The selec…
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Tianlong Chen, Jonathan Frankle, Shiyu Chang +4
The computer vision world has been re-gaining enthusiasm in various pre-trained models, including both classical ImageNet supervised pre-training and recently emerged self-supervis…
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
Tianlong Chen, Jonathan Frankle, Shiyu Chang +4
In natural language processing (NLP), enormous pre-trained models like BERT have become the standard starting point for training on a range of downstream tasks, and similar trends…
Invariant Rationalization
Shiyu Chang, Yang Zhang, Mo Yu +1
Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction…
A Game Theoretic Approach to Class-wise Selective Rationalization
Shiyu Chang, Yang Zhang, Mo Yu +1
Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. The selection can be optimized post…