Do Current Multi-Task Optimization Methods in Deep Learning Even Help?

Do Current Multi-Task Optimization Methods in Deep Learning Even Help?

23 September 2022

Behrooz Ghorbani

Justin Gilmer

Papers citing "Do Current Multi-Task Optimization Methods in Deep Learning Even Help?"

11 / 11 papers shown

Title
Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate Zhiqi Bu Xiaomeng Jin Bhanukiran Vinzamuri Anil Ramakrishna Kai-Wei Chang V. Cevher Mingyi Hong MU 77 6 0 29 Oct 2024
Federated Communication-Efficient Multi-Objective Optimization Baris Askin Pranay Sharma Gauri Joshi Carlee Joe-Wong FedML 36 1 0 21 Oct 2024
Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets Tianjian Li Haoran Xu Weiting Tan Kenton Murray Daniel Khashabi 35 1 0 06 Oct 2024
Can Optimization Trajectories Explain Multi-Task Transfer? David Mueller Mark Dredze Nicholas Andrews 35 1 0 26 Aug 2024
Enhancing Domain Adaptation through Prompt Gradient Alignment Hoang Phan Lam C. Tran Quyen Tran Trung Le 38 0 0 13 Jun 2024
FAMO: Fast Adaptive Multitask Optimization B. Liu Yihao Feng Peter Stone Qian Liu 19 26 0 06 Jun 2023
Differentiable Random Partition Models Thomas M. Sutter Alain Ryser Joram Liebeskind Julia E. Vogt 26 3 0 26 May 2023
Scaling Laws for Multilingual Neural Machine Translation Patrick Fernandes Behrooz Ghorbani Xavier Garcia Markus Freitag Orhan Firat 17 28 0 19 Feb 2023
In Defense of the Unitary Scalarization for Deep Multi-Task Learning Vitaly Kurin Alessandro De Palma Ilya Kostrikov Shimon Whiteson M. P. Kumar 17 71 0 11 Jan 2022
Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits Julia Kreutzer David Vilar Artem Sokolov 43 15 0 13 Oct 2021
Efficiently Identifying Task Groupings for Multi-Task Learning Christopher Fifty Ehsan Amid Zhe Zhao Tianhe Yu Rohan Anil Chelsea Finn 201 235 1 10 Sep 2021