Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

14 October 2020

Henrik Kretzschmar

Papers citing "Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout"

36 / 136 papers shown

Title
Do Current Multi-Task Optimization Methods in Deep Learning Even Help? Derrick Xin Behrooz Ghorbani Ankush Garg Orhan Firat Justin Gilmer MoMe 69 63 0 23 Sep 2022
Curbing Task Interference using Representation Similarity-Guided Multi-Task Feature Sharing Naresh Gurulingan Elahe Arani Bahram Zonooz 16 1 0 19 Aug 2022
Beyond Transfer Learning: Co-finetuning for Action Localisation Anurag Arnab Xuehan Xiong A. Gritsenko Rob Romijnders Josip Djolonga Mostafa Dehghani Chen Sun Mario Lucic Cordelia Schmid 30 8 0 08 Jul 2022
Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression Meishu Song Zijiang Yang Andreas Triantafyllopoulos Xin Jing Vincent Karas Xie Jiangjian Zixing Zhang Yamamoto Yoshiharu Bjoern W. Schuller 14 6 0 22 Jun 2022
Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization Adrián Javaloy Maryam Meghdadi Isabel Valera 19 26 0 09 Jun 2022
Improving Multi-Task Generalization via Regularizing Spurious Correlation Ziniu Hu Zhe Zhao Xinyang Yi Tiansheng Yao Lichan Hong Yizhou Sun Ed H. Chi OOD LRM 85 29 0 19 May 2022
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving Yunpeng Zhang Zheng Hua Zhu Wenzhao Zheng Junjie Huang Guan Huang Jie Zhou Jiwen Lu 25 187 0 19 May 2022
Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports Arijit Sehanobish M. Sandora Nabila Abraham Jayashri Pawar Danielle Torres Anasuya Das M. Becker Richard Herzog Benjamin Odry Ron Vianu 11 3 0 06 May 2022
Universal Representations: A Unified Look at Multiple Task and Domain Learning Wei-Hong Li Xialei Liu Hakan Bilen SSL OOD 28 27 0 06 Apr 2022
Controllable Dynamic Multi-Task Architectures Dripta S. Raychaudhuri Yumin Suh S. Schulter Xiang Yu M. Faraki A. Roy-Chowdhury Manmohan Chandraker 16 32 0 28 Mar 2022
LibMTL: A Python Library for Multi-Task Learning Baijiong Lin Yu Zhang OffRL AI4CE 25 37 0 27 Mar 2022
InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding Hanrong Ye Dan Xu ViT 19 84 0 15 Mar 2022
MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks Yun He Xuening Feng Cheng Cheng Geng Ji Yunsong Guo James Caverlee 6 42 0 14 Mar 2022
On Steering Multi-Annotations per Sample for Multi-Task Learning Yuan Li Yiwen Guo Qizhang Li Hongzhi Zhang W. Zuo 17 0 0 06 Mar 2022
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training Joya Chen Kai Xu Yuhui Wang Yifei Cheng Angela Yao 19 7 0 28 Feb 2022
Auto-Lambda: Disentangling Dynamic Task Relationships Shikun Liu Stephen James Andrew J. Davison Edward Johns 26 75 0 07 Feb 2022
Multi-Task Learning as a Bargaining Game Aviv Navon Aviv Shamsian Idan Achituve Haggai Maron Kenji Kawaguchi Gal Chechik Ethan Fetaya 17 140 0 02 Feb 2022
GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting Zhao Chen Vincent Casser Henrik Kretzschmar Dragomir Anguelov 26 5 0 16 Jan 2022
In Defense of the Unitary Scalarization for Deep Multi-Task Learning Vitaly Kurin Alessandro De Palma Ilya Kostrikov Shimon Whiteson M. P. Kumar 28 73 0 11 Jan 2022
Improving evidential deep learning via multi-task learning Dongpin Oh Bonggun Shin EDL UQCV 17 24 0 17 Dec 2021
Learning Multiple Dense Prediction Tasks from Partially Annotated Data Weihong Li Xialei Liu Hakan Bilen 37 39 0 29 Nov 2021
Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning Baijiong Lin Feiyang Ye Yu Zhang Ivor W. Tsang 31 93 0 20 Nov 2021
Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder Joakim Bruslund Haurum Meysam Madadi Sergio Escalera T. Moeslund AI4CE 8 8 0 15 Nov 2021
Conflict-Averse Gradient Descent for Multi-task Learning Bo Liu Xingchao Liu Xiaojie Jin Peter Stone Qiang Liu 33 297 0 26 Oct 2021
Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set Mao Ye Qiang Liu 15 9 0 17 Oct 2021
Improved optimization strategies for deep Multi-Task Networks Lucas Pascal Pietro Michiardi Xavier Bost B. Huet Maria A. Zuluaga 27 6 0 21 Sep 2021
Efficiently Identifying Task Groupings for Multi-Task Learning Christopher Fifty Ehsan Amid Zhe Zhao Tianhe Yu Rohan Anil Chelsea Finn 201 238 1 10 Sep 2021
Multi-Task Self-Training for Learning General Representations Golnaz Ghiasi Barret Zoph E. D. Cubuk Quoc V. Le Tsung-Yi Lin SSL 18 100 0 25 Aug 2021
Contextualizing Meta-Learning via Learning to Decompose Han-Jia Ye Da-Wei Zhou Lanqing Hong Zhenguo Li Xiu-Shen Wei De-Chuan Zhan 18 6 0 15 Jun 2021
Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning Yuyan Wang Xuezhi Wang Alex Beutel Flavien Prost Jilin Chen Ed H. Chi FaML 21 46 0 04 Jun 2021
CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration Changnan Xiao Haosen Shi Jiajun Fan Shihong Deng Haiyan Yin 8 0 0 09 May 2021
RotoGrad: Gradient Homogenization in Multitask Learning Adrián Javaloy Isabel Valera 21 85 0 03 Mar 2021
Adversarial Imaging Pipelines Buu Phan Fahim Mannan Felix Heide AAML 14 26 0 07 Feb 2021
Measuring and Harnessing Transference in Multi-Task Learning Christopher Fifty Ehsan Amid Zhe Zhao Tianhe Yu Rohan Anil Chelsea Finn 25 15 0 29 Oct 2020
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 278 2,888 0 15 Sep 2016
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 179 1,185 0 30 Nov 2014