Multitask Learning Can Improve Worst-Group Outcomes

Multitask Learning Can Improve Worst-Group Outcomes

5 December 2023

Atharva Kulkarni

Amrith Rajagopal Setlur

Aditi Raghunathan

Ameet Talwalkar

Graham Neubig

Papers citing "Multitask Learning Can Improve Worst-Group Outcomes"

6 / 6 papers shown

Title
Simple and Fast Group Robustness by Automatic Feature Reweighting Shi Qiu Andres Potapczynski Pavel Izmailov A. Wilson OOD 70 53 0 19 Jun 2023
Understanding Why Generalized Reweighting Does Not Improve Over ERM Runtian Zhai Chen Dan Zico Kolter Pradeep Ravikumar OOD 44 27 0 28 Jan 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 305 7,443 0 11 Nov 2021
A Fine-Grained Analysis on Distribution Shift Olivia Wiles Sven Gowal Florian Stimberg Sylvestre-Alvise Rebuffi Ira Ktena Krishnamurthy Dvijotham A. Cemgil OOD 225 202 0 21 Oct 2021
Gradient Matching for Domain Generalization Yuge Shi Jeffrey S. Seely Philip H. S. Torr Siddharth Narayanaswamy Awni Y. Hannun Nicolas Usunier Gabriel Synnaeve OOD 216 246 0 20 Apr 2021
An Investigation of Why Overparameterization Exacerbates Spurious Correlations Shiori Sagawa Aditi Raghunathan Pang Wei Koh Percy Liang 152 371 0 09 May 2020