Timezone: »

Auxiliary Task Reweighting for Minimum-data Learning
Baifeng Shi · Judy Hoffman · Kate Saenko · Trevor Darrell · Huijuan Xu

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #776

Supervised learning requires a large amount of training data, limiting its application where labeled data is scarce. To compensate for data scarcity, one possible method is to utilize auxiliary tasks to provide additional supervision for the main task. Assigning and optimizing the importance weights for different auxiliary tasks remains an crucial and largely understudied research question. In this work, we propose a method to automatically reweight auxiliary tasks in order to reduce the data requirement on the main task. Specifically, we formulate the weighted likelihood function of auxiliary tasks as a surrogate prior for the main task. By adjusting the auxiliary task weights to minimize the divergence between the surrogate prior and the true prior of the main task, we obtain a more accurate prior estimation, achieving the goal of minimizing the required amount of training data for the main task and avoiding a costly grid search. In multiple experimental settings (e.g. semi-supervised learning, multi-label classification), we demonstrate that our algorithm can effectively utilize limited labeled data of the main task with the benefit of auxiliary tasks compared with previous task reweighting methods. We also show that under extreme cases with only a few extra examples (e.g. few-shot domain adaptation), our algorithm results in significant improvement over the baseline. Our code and video is available at https://sites.google.com/view/auxiliary-task-reweighting.

Author Information

Baifeng Shi (Peking University)
Judy Hoffman (Georgia Institute of Technology)
Kate Saenko (Boston University & MIT-IBM Watson AI Lab, IBM Research)
Kate Saenko

Kate is an AI Research Scientist at FAIR, Meta and a Full Professor of Computer Science at Boston University (currently on leave) where she leads the Computer Vision and Learning Group. Kate received a PhD in EECS from MIT and did postdoctoral training at UC Berkeley and Harvard. Her research interests are in Artificial Intelligence with a focus on out-of-distribution learning, dataset bias, domain adaptation, vision and language understanding, and other topics in deep learning. Past academic positions Consulting professor at the MIT-IBM Watson AI Lab 2019-2022. Assistant Professor, Computer Science Department at UMass Lowell Postdoctoral Researcher, International Computer Science Institute Visiting Scholar, UC Berkeley EECS Visiting Postdoctoral Fellow, SEAS, Harvard University

Trevor Darrell (UC Berkeley)
Huijuan Xu (University of California, Berkeley)

She is a postdoctoral scholar in the EECS department at UC Berkeley advised by Prof. Trevor Darrell. She received her PhD degree from the computer science department at Boston University in 2018 advised by Prof. Kate Saenko. Her research focuses on deep learning, computer vision and natural language processing, particularly in the area of action understanding in video. Her R-C3D work has received the Most Innovative Award in ActivityNet Challenge 2017. She interned at Disney Research, Pittsburgh with Prof. Leonid Sigal.

More from the Same Authors