v1v2v3v4 (latest)

Gradient Surgery for Multi-Task Learning

Neural Information Processing Systems (NeurIPS), 2020

19 January 2020

Abhishek Gupta

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)

Papers citing "Gradient Surgery for Multi-Task Learning"

50 / 741 papers shown

Title
Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?International Conference on Learning Representations (ICLR), 2022 Y. Fu Shunyao Zhang Shan-Hung Wu Cheng Wan Yingyan Lin AAML 207 77 0 16 Mar 2022
Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning Qinjie Lin Han Liu B. Sengupta OffRL 94 12 0 14 Mar 2022
MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary TasksThe Web Conference (WWW), 2022 Yun He Xuening Feng Cheng Cheng Geng Ji Yunsong Guo James Caverlee 105 57 0 14 Mar 2022
Multi-Agent Policy Transfer via Task Relationship ModelingScience China Information Sciences (Sci. China Inf. Sci.), 2022 Rongjun Qin F. Chen Tonghan Wang Lei Yuan Xiaoran Wu Zongzhang Zhang Chongjie Zhang Yang Yu 155 27 0 09 Mar 2022
On Steering Multi-Annotations per Sample for Multi-Task Learning Yuan Li Yiwen Guo Qizhang Li Hongzhi Zhang W. Zuo 98 0 0 06 Mar 2022
Implicit Kinematic Policies: Unifying Joint and Cartesian Action Spaces in End-to-End Robot LearningIEEE International Conference on Robotics and Automation (ICRA), 2022 Aditya Ganapathi Peter R. Florence Jacob Varley Kaylee Burns Ken Goldberg Andy Zeng 250 18 0 03 Mar 2022
Continuous-Time Meta-Learning with Forward Mode DifferentiationInternational Conference on Learning Representations (ICLR), 2022 T. Deleu David Kanaa Leo Feng Giancarlo Kerg Yoshua Bengio Guillaume Lajoie Pierre-Luc Bacon 152 19 0 02 Mar 2022
Structured Multi-task Learning for Molecular Property PredictionInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Shengchao Liu Meng Qu Zuobai Zhang Huiyu Cai Jian Tang 135 27 0 22 Feb 2022
Cross-Task Knowledge Distillation in Multi-Task RecommendationAAAI Conference on Artificial Intelligence (AAAI), 2022 Chenxiao Yang Junwei Pan Xiaofeng Gao Tingyu Jiang Dapeng Liu Guihai Chen 160 53 0 20 Feb 2022
Orthogonalising gradients to speed up neural network optimisation Mark Tuddenham Adam Prugel-Bennett Jonathan Hare ODL 108 12 0 14 Feb 2022
Robust Policy Learning over Multiple Uncertainty SetsInternational Conference on Machine Learning (ICML), 2022 Annie Xie Shagun Sodhani Chelsea Finn Joelle Pineau Amy Zhang OOD OffRL 184 21 0 14 Feb 2022
Auto-Lambda: Disentangling Dynamic Task Relationships Shikun Liu Stephen James Andrew J. Davison Edward Johns 192 88 0 07 Feb 2022
Multi-Task Learning as a Bargaining GameInternational Conference on Machine Learning (ICML), 2022 Aviv Navon Aviv Shamsian Idan Achituve Haggai Maron Kenji Kawaguchi Gal Chechik Ethan Fetaya 197 200 0 02 Feb 2022
Dissecting the impact of different loss functions with gradient surgery Hong Xuan Robert Pless 72 1 0 27 Jan 2022
Gap Minimization for Knowledge Sharing and TransferJournal of machine learning research (JMLR), 2022 Boyu Wang Jorge Armando Mendez Mendez Changjian Shui Fan Zhou Di Wu Gezheng Xu Christian Gagné Eric Eaton 205 12 0 26 Jan 2022
A Multi-modal Fusion Framework Based on Multi-task Correlation Learning for Cancer Prognosis Prediction Kaiwen Tan Weixian Huang Xiaofeng Liu Jinlong Hu Shoubin Dong 93 48 0 22 Jan 2022
A Novel Framework to Jointly Compress and Index Remote Sensing Images for Efficient Content-Based RetrievalIEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2022 Gencer Sumbul Jun Xiang Nimisha Thekke Madam Begüm Demir 134 1 0 17 Jan 2022
GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting Zhao Chen Vincent Casser Henrik Kretzschmar Dragomir Anguelov 100 5 0 16 Jan 2022
In Defense of the Unitary Scalarization for Deep Multi-Task LearningNeural Information Processing Systems (NeurIPS), 2022 Vitaly Kurin Alessandro De Palma Ilya Kostrikov Shimon Whiteson M. P. Kumar 210 84 0 11 Jan 2022
Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning Ziyang Tang Yihao Feng Qiang Liu OffRL 149 1 0 01 Jan 2022
Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic EnvironmentsFrontiers in Neurorobotics (FN), 2021 A. Iyer Karan Grewal Akash Velu Lucas O. Souza Jérémy Forest Subutai Ahmad AI4CE 190 53 0 31 Dec 2021
Parameter Differentiation based Multilingual Neural Machine TranslationAAAI Conference on Artificial Intelligence (AAAI), 2021 Qian Wang Jiajun Zhang 152 21 0 27 Dec 2021
Manifold embedding data-driven mechanicsJournal of the mechanics and physics of solids (JMPS), 2021 B. Bahmani WaiChing Sun PINN AI4CE 120 10 0 18 Dec 2021
Improving evidential deep learning via multi-task learning Dongpin Oh Bonggun Shin EDL UQCV 148 30 0 17 Dec 2021
Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module Wei-Cheng Tseng Wei Wei Da-Cheng Juan Min Sun 117 2 0 14 Dec 2021
E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation Jie Zhu Huabin Huang Banghuai Li Leye Wang 133 14 0 14 Dec 2021
Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text Qing Li Boqing Gong Huayu Chen Dan Kondratyuk Xianzhi Du Ming-Hsuan Yang Matthew A. Brown ViT 81 18 0 14 Dec 2021
Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training Haofei Zhang Jiarui Duan Mengqi Xue Mingli Song Li Sun Xiuming Zhang ViT AI4CE 153 16 0 07 Dec 2021
A generic physics-informed neural network-based framework for reliability assessment of multi-state systems Taotao Zhou Xiaoge Zhang E. Droguett A. Mosleh AI4CE 185 35 0 01 Dec 2021
Learning Multiple Dense Prediction Tasks from Partially Annotated Data Weihong Li Xialei Liu Hakan Bilen 208 47 0 29 Nov 2021
Cross-Task Consistency Learning Framework for Multi-Task Learning Akihiro Nakano Shi Chen K. Demachi CVBM 161 3 0 28 Nov 2021
PolyViT: Co-training Vision Transformers on Images, Videos and Audio Valerii Likhosherstov Anurag Arnab K. Choromanski Mario Lucic Yi Tay Adrian Weller Mostafa Dehghani ViT 144 79 0 25 Nov 2021
ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning V. Aribandi Yi Tay Tal Schuster J. Rao H. Zheng ... Jianmo Ni Jai Gupta Kai Hui Sebastian Ruder Donald Metzler MoE 204 224 0 22 Nov 2021
Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning Xiaoyuan Zhang Feiyang Ye Yu Zhang Ivor W. Tsang 185 116 0 20 Nov 2021
Deep Safe Multi-Task Learning Zhixiong Yue Feiyang Ye Yu Zhang Christy Jie Liang Ivor W. Tsang 113 3 0 20 Nov 2021
SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation Hang Zhou Sarah Taylor David Greenwood Michal Mackiewicz UQCV MDE 189 11 0 18 Nov 2021
Multi-Task Neural Processes Jiayi Shen Xiantong Zhen M. Worring Ling Shao BDL 130 9 0 10 Nov 2021
Variational Multi-Task Learning with Gumbel-Softmax PriorsNeural Information Processing Systems (NeurIPS), 2021 Jiayi Shen Xiantong Zhen M. Worring Ling Shao 106 35 0 09 Nov 2021
Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning Wenlong Huang Igor Mordatch Pieter Abbeel Deepak Pathak 204 68 0 04 Nov 2021
An Empirical Study of Training End-to-End Vision-and-Language TransformersComputer Vision and Pattern Recognition (CVPR), 2021 Zi-Yi Dou Yichong Xu Zhe Gan Jianfeng Wang Shuohang Wang ... Pengchuan Zhang Lu Yuan Nanyun Peng Zicheng Liu Michael Zeng VLM 193 419 0 03 Nov 2021
Towards Fairness-Aware Federated LearningIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021 Yuxin Shi Han Yu Cyril Leung FedML 154 106 0 02 Nov 2021
Meta-Learning to Improve Pre-TrainingNeural Information Processing Systems (NeurIPS), 2021 Aniruddh Raghu Jonathan Lorraine Simon Kornblith Matthew B. A. McDermott David Duvenaud 141 34 0 02 Nov 2021
Procedural Generalization by Planning with Self-Supervised World ModelsInternational Conference on Learning Representations (ICLR), 2021 Ankesh Anand Jacob Walker Yazhe Li Eszter Vértes Julian Schrittwieser Sherjil Ozair T. Weber Jessica B. Hamrick 121 34 0 02 Nov 2021
Conflict-Averse Gradient Descent for Multi-task Learning Bo Liu Xingchao Liu Xiaojie Jin Peter Stone Qiang Liu 252 407 0 26 Oct 2021
AutoMTL: A Programming Framework for Automating Efficient Multi-Task LearningNeural Information Processing Systems (NeurIPS), 2021 Lijun Zhang Xiao Liu Hui Guan 255 26 0 25 Oct 2021
Game of Gradients: Mitigating Irrelevant Clients in Federated LearningAAAI Conference on Artificial Intelligence (AAAI), 2021 Lokesh Nagalapatti Mahdi S. Hosseini FedML 124 86 0 23 Oct 2021
Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning Yi-Chen Chen Shu-Wen Yang Cheng-Kuang Lee Simon See Hung-yi Lee SSL 90 13 0 18 Oct 2021
Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set Mao Ye Qiang Liu 199 12 0 17 Oct 2021
Semi-supervised Multi-task Learning for Semantics and Depth Yufeng Wang Yi-Hsuan Tsai Wei-Chih Hung Wenrui Ding Shuo Liu Ming-Hsuan Yang 133 28 0 14 Oct 2021
Balancing Average and Worst-case Accuracy in Multitask Learning Paul Michel Sebastian Ruder Dani Yogatama 133 13 0 12 Oct 2021