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"

40 / 740 papers shown

Title
Multi-Task Reinforcement Learning with Context-based RepresentationsInternational Conference on Machine Learning (ICML), 2021 Shagun Sodhani Amy Zhang Joelle Pineau 200 216 0 11 Feb 2021
Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization T. Deist Monika Grewal F. Dankers Tanja Alderliesten Peter A. N. Bosman 118 21 0 08 Feb 2021
Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel PairsKnowledge-Based Systems (KBS), 2021 Quan Feng Songcan Chen 109 6 0 29 Jan 2021
FedH2L: Federated Learning with Model and Statistical Heterogeneity Yiying Li Wei Zhou Huaimin Wang Haibo Mi Timothy M. Hospedales FedML 176 30 0 27 Jan 2021
RomeBERT: Robust Training of Multi-Exit BERT Shijie Geng Shiyang Feng Zuohui Fu Zelong Li 120 30 0 24 Jan 2021
MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks J. Pata Javier Mauricio Duarte J. Vlimant M. Pierini M. Spiropulu 322 82 0 21 Jan 2021
Towards Continual Reinforcement Learning: A Review and PerspectivesJournal of Artificial Intelligence Research (JAIR), 2020 Khimya Khetarpal Matthew D Riemer Irina Rish Doina Precup CLL OffRL 298 360 0 25 Dec 2020
Atlas-ISTN: Joint Segmentation, Registration and Atlas Construction with Image-and-Spatial Transformer Networks Matthew Sinclair A. Schuh K. Hahn K. Petersen Ying Bai James Batten M. Schaap Ben Glocker 147 36 0 18 Dec 2020
Detecting 32 Pedestrian Attributes for Autonomous Vehicles Taylor Mordan Matthieu Cord P. Pérez Alexandre Alahi 119 28 0 04 Dec 2020
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement LearningInternational Conference on Machine Learning (ICML), 2020 Dong-Ki Kim Miao Liu Matthew D Riemer Chuangchuang Sun Marwa Abdulhai Golnaz Habibi Sebastian Lopez-Cot Gerald Tesauro Jonathan P. How 185 61 0 31 Oct 2020
Measuring and Harnessing Transference in Multi-Task Learning Christopher Fifty Ehsan Amid Zhe Zhao Tianhe Yu Rohan Anil Chelsea Finn 131 15 0 29 Oct 2020
Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control Zhiyuan Xu Kun Wu Zhengping Che Jian Tang Jieping Ye CLL OffRL 177 52 0 15 Oct 2020
Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout Zhao Chen Jiquan Ngiam Yanping Huang Thang Luong Henrik Kretzschmar Yuning Chai Dragomir Anguelov 120 254 0 14 Oct 2020
Controllable Pareto Multi-Task Learning Xi Lin Zhiyuan Yang Qingfu Zhang Sam Kwong MoE 182 75 0 13 Oct 2020
Contrast and Classify: Training Robust VQA Models Yash Kant A. Moudgil Dhruv Batra Devi Parikh Harsh Agrawal 79 5 0 13 Oct 2020
Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models Zirui Wang Yulia Tsvetkov Orhan Firat Yuan Cao 251 221 0 12 Oct 2020
A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix T. Doan Mehdi Abbana Bennani Bogdan Mazoure Guillaume Rabusseau Pierre Alquier CLL 223 92 0 07 Oct 2020
On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment Zirui Wang Zachary Chase Lipton Yulia Tsvetkov 111 32 0 06 Oct 2020
Supervised Seeded Iterated Learning for Interactive Language Learning Yuchen Lu Soumye Singhal Florian Strub Olivier Pietquin Aaron Courville 85 9 0 06 Oct 2020
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less DataInternational Conference on Learning Representations (ICLR), 2020 Jonathan Pilault Amine Elhattami C. Pal CLL MoE 194 102 0 19 Sep 2020
Multi-Task Learning with Deep Neural Networks: A Survey M. Crawshaw CVBM 330 690 0 10 Sep 2020
A Survey on Negative TransferIEEE/CAA Journal of Automatica Sinica (JCAS), 2020 Wen Zhang Lingfei Deng Lei Zhang Dongrui Wu AAML 321 268 0 02 Sep 2020
HydaLearn: Highly Dynamic Task Weighting for Multi-task Learning with Auxiliary Tasks Sam Verboven M. H. Chaudhary Jeroen Berrevoets Wouter Verbeke 97 7 0 26 Aug 2020
Small Towers Make Big Differences Yuyan Wang Zhe Zhao Bo Dai Christopher Fifty Dong Lin Lichan Hong Ed H. Chi 134 10 0 13 Aug 2020
SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated DataEuropean Conference on Computer Vision (ECCV), 2020 Tyler Lixuan Zhu Per Karlsson C. Bregler 3DH 150 30 0 30 Jul 2020
La-MAML: Look-ahead Meta Learning for Continual LearningNeural Information Processing Systems (NeurIPS), 2020 Gunshi Gupta Karmesh Yadav Liam Paull CLL VLM 191 79 0 27 Jul 2020
Knowledge Distillation for Multi-task Learning Weihong Li Hakan Bilen MoMe 164 83 0 14 Jul 2020
Local Stochastic Approximation: A Unified View of Federated Learning and Distributed Multi-Task Reinforcement Learning Algorithms Thinh T. Doan FedML 94 10 0 24 Jun 2020
Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent Mehdi Abbana Bennani Thang Doan Masashi Sugiyama CLL 274 68 0 21 Jun 2020
A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning Sihan Zeng Aqeel Anwar Thinh T. Doan A. Raychowdhury Justin Romberg 144 42 0 08 Jun 2020
Learning Transferable Concepts in Deep Reinforcement Learning Diego Gomez Nicanor Quijano Luis Felipe Giraldo CLL SSL 125 0 0 16 May 2020
Multi-Task Learning in Histo-pathology for Widely Generalizable Model Jevgenij Gamper Navid Alemi Koohbanani Nasir M. Rajpoot 96 7 0 09 May 2020
Multi-task pre-training of deep neural networks for digital pathologyIEEE journal of biomedical and health informatics (JBHI), 2020 Romain Mormont Pierre Geurts R. Marée 47 57 0 05 May 2020
Finding the Optimal Network Depth in Classification Tasks Bartosz Wójcik Maciej Wołczyk Klaudia Bałazy Jacek Tabor 74 0 0 17 Apr 2020
Meta-Learning in Neural Networks: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 Timothy M. Hospedales Antreas Antoniou P. Micaelli Amos Storkey OOD 499 2,278 0 11 Apr 2020
Multi-Task Reinforcement Learning with Soft ModularizationNeural Information Processing Systems (NeurIPS), 2020 Ruihan Yang Huazhe Xu Yi Wu Xiaolong Wang 130 205 0 30 Mar 2020
DisCor: Corrective Feedback in Reinforcement Learning via Distribution CorrectionNeural Information Processing Systems (NeurIPS), 2020 Aviral Kumar Abhishek Gupta Sergey Levine OffRL 139 115 0 16 Mar 2020
Lipschitz standardization for multivariate learning Adrián Javaloy Isabel Valera 69 0 0 26 Feb 2020
Rewriting History with Inverse RL: Hindsight Inference for Policy ImprovementNeural Information Processing Systems (NeurIPS), 2020 Benjamin Eysenbach Xinyang Geng Sergey Levine Ruslan Salakhutdinov OffRL 159 91 0 25 Feb 2020
A Survey on Multi-Task Learning Yu Zhang Qiang Yang AIMat 812 2,545 0 25 Jul 2017