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 / 742 papers shown

Title
Balancing Average and Worst-case Accuracy in Multitask Learning Paul Michel Sebastian Ruder Dani Yogatama 133 13 0 12 Oct 2021
Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning Trevor A. McInroe Lukas Schafer Stefano V. Albrecht OffRL 96 8 0 11 Oct 2021
Learning Multi-Objective Curricula for Robotic Policy Learning Jikun Kang Miao Liu Abhinav Gupta C. Pal Xue Liu Jie Fu 172 6 0 06 Oct 2021
ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods Victor Schmidt A. Luccioni Mélisande Teng Tianyu Zhang Alexia Reynaud ... Gautier Cosne Adrien Juraver V. Vardanyan Alex Hernandez-Garcia Yoshua Bengio GAN AI4CE 131 25 0 06 Oct 2021
Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning Seanie Lee Haebeom Lee Juho Lee Sung Ju Hwang MoMe CLL 248 19 0 06 Oct 2021
Fast Line Search for Multi-Task Learning A. Filatov D. Merkulov 71 0 0 02 Oct 2021
Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets F. Ebert Yanlai Yang Karl Schmeckpeper Bernadette Bucher G. Georgakis Kostas Daniilidis Chelsea Finn Sergey Levine 329 271 0 27 Sep 2021
Improved optimization strategies for deep Multi-Task Networks Lucas Pascal Pietro Michiardi Xavier Bost B. Huet Maria A. Zuluaga 168 6 0 21 Sep 2021
Lifelong Robotic Reinforcement Learning by Retaining Experiences Annie Xie Chelsea Finn OffRL CLL 230 50 0 19 Sep 2021
Multi-Task Learning in Natural Language Processing: An Overview Shijie Chen Yu Zhang Qiang Yang AIMat 207 147 0 19 Sep 2021
SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learning M. Crawshaw Jana Kosecka 113 8 0 16 Sep 2021
Conservative Data Sharing for Multi-Task Offline Reinforcement Learning Tianhe Yu Aviral Kumar Yevgen Chebotar Karol Hausman Sergey Levine Chelsea Finn OffRL 149 82 0 16 Sep 2021
On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation Dan Iter David Grangier 165 11 0 15 Sep 2021
Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative Lucio Dery Paul Michel Ameet Talwalkar Graham Neubig CLL 156 38 0 15 Sep 2021
Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction Xuming Hu Chenwei Zhang Yawen Yang Xiaohe Li Li Lin Lijie Wen Philip S. Yu 109 62 0 14 Sep 2021
Improving Multilingual Translation by Representation and Gradient RegularizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Yilin Yang Akiko Eriguchi Alexandre Muzio Prasad Tadepalli Stefan Lee Hany Hassan 97 41 0 10 Sep 2021
Efficiently Identifying Task Groupings for Multi-Task LearningNeural Information Processing Systems (NeurIPS), 2021 Christopher Fifty Ehsan Amid Zhe Zhao Tianhe Yu Rohan Anil Chelsea Finn 422 281 1 10 Sep 2021
Fishr: Invariant Gradient Variances for Out-of-Distribution GeneralizationInternational Conference on Machine Learning (ICML), 2021 Alexandre Ramé Corentin Dancette Matthieu Cord OOD 243 240 0 07 Sep 2021
Multi-Task Self-Training for Learning General RepresentationsIEEE International Conference on Computer Vision (ICCV), 2021 Golnaz Ghiasi Barret Zoph E. D. Cubuk Quoc V. Le Nayeon Lee SSL 144 108 0 25 Aug 2021
Auxiliary Task Update Decomposition: The Good, The Bad and The NeutralInternational Conference on Learning Representations (ICLR), 2021 Lucio Dery Yann N. Dauphin David Grangier MoMe 123 29 0 25 Aug 2021
Domain Generalization via Gradient Surgery Lucas Mansilla Rodrigo Echeveste Diego H. Milone Enzo Ferrante OOD 154 91 0 03 Aug 2021
Multi-Task Learning in Utterance-Level and Segmental-Level Spoof Detection Lin Zhang Xin Wang Erica Cooper Junichi Yamagishi 82 34 0 29 Jul 2021
Autonomous Reinforcement Learning via Subgoal CurriculaNeural Information Processing Systems (NeurIPS), 2021 Archit Sharma Abhishek Gupta Sergey Levine Karol Hausman Chelsea Finn 135 31 0 27 Jul 2021
Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings B. Bahmani WaiChing Sun PINN AI4CE 144 20 0 24 Jul 2021
Multi-modal Residual Perceptron Network for Audio-Video Emotion RecognitionItalian National Conference on Sensors (INS), 2021 Xin Chang W. Skarbek 130 20 0 21 Jul 2021
Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research J. Luis E. Crawley B. Cameron OffRL 166 6 0 07 Jul 2021
Relational graph convolutional networks for predicting blood-brain barrier penetration of drug molecules Yan Ding Xiaoqian Jiang Yejin Kim GNN 107 22 0 04 Jul 2021
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation Nicklas Hansen H. Su Xiaolong Wang OffRL 235 155 0 01 Jul 2021
Modularity in Reinforcement Learning via Algorithmic Independence in Credit AssignmentInternational Conference on Machine Learning (ICML), 2021 Michael Chang Sid Kaushik Sergey Levine Thomas Griffiths 166 8 0 28 Jun 2021
Mix and Mask Actor-Critic Methods Dom Huh 54 1 0 24 Jun 2021
Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence ModelingNeural Information Processing Systems (NeurIPS), 2021 Hongyu Gong Yun Tang J. Pino Xian Li 92 12 0 21 Jun 2021
Same State, Different Task: Continual Reinforcement Learning without InterferenceAAAI Conference on Artificial Intelligence (AAAI), 2021 Samuel Kessler Jack Parker-Holder Philip J. Ball S. Zohren Stephen J. Roberts CLL OffRL 170 53 0 05 Jun 2021
Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task LearningKnowledge Discovery and Data Mining (KDD), 2021 Yuyan Wang Xuezhi Wang Alex Beutel Flavien Prost Jilin Chen Ed H. Chi FaML 102 53 0 04 Jun 2021
Efficient and robust multi-task learning in the brain with modular latent primitives Christian David Márton Léo Gagnon Guillaume Lajoie Kanaka Rajan 105 9 0 28 May 2021
Privacy-Preserving Constrained Domain Generalization via Gradient AlignmentIEEE Transactions on Knowledge and Data Engineering (TKDE), 2021 Chris Xing Tian Haoliang Li Yufei Wang Shiqi Wang 152 7 0 14 May 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 153 0 0 09 May 2021
Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study D. Kollias V. Sharmanska Stefanos Zafeiriou CVBM 142 241 0 08 May 2021
SpeechNet: A Universal Modularized Model for Speech Processing Tasks Yi-Chen Chen Po-Han Chi Shu-Wen Yang Kai-Wei Chang Jheng-hao Lin Sung-Feng Huang Da-Rong Liu Chi-Liang Liu Cheng-Kuang Lee Hung-yi Lee MoE 170 18 0 07 May 2021
Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential EquationsIEEE International Joint Conference on Neural Network (IJCNN), 2021 Pongpisit Thanasutives M. Numao Ken-ichi Fukui AI4CE 125 32 0 29 Apr 2021
Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human InterventionIEEE International Conference on Robotics and Automation (ICRA), 2021 Abhishek Gupta Justin Yu Tony Zhao Vikash Kumar Aaron Rovinsky Kelvin Xu Thomas Devlin Sergey Levine OffRL 170 111 0 22 Apr 2021
ImageNet-21K Pretraining for the Masses T. Ridnik Emanuel Ben-Baruch Asaf Noy Lihi Zelnik-Manor SSeg VLM CLIP 529 820 0 22 Apr 2021
MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale Dmitry Kalashnikov Jacob Varley Yevgen Chebotar Benjamin Swanson Rico Jonschkowski Chelsea Finn Sergey Levine Karol Hausman OffRL 225 301 0 16 Apr 2021
Adaptive Sparse Transformer for Multilingual Translation Hongyu Gong Xian Li Dmitriy Genzel 97 14 0 15 Apr 2021
Continual Learning for Text Classification with Information Disentanglement Based RegularizationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 Yufan Huang Yanzhe Zhang Jiaao Chen Xuezhi Wang Diyi Yang CLL 121 121 0 12 Apr 2021
Physics-informed neural networks for the shallow-water equations on the sphereJournal of Computational Physics (JCP), 2021 Alexander Bihlo R. Popovych 122 89 0 01 Apr 2021
Universal Representation Learning from Multiple Domains for Few-shot ClassificationIEEE International Conference on Computer Vision (ICCV), 2021 Weihong Li Xialei Liu Hakan Bilen SSL OOD VLM 141 107 0 25 Mar 2021
Spectral Reconstruction and Disparity from Spatio-Spectrally Coded Light Fields via Multi-Task Deep LearningInternational Conference on 3D Vision (3DV), 2021 Maximilian Schambach Jiayang Shi M. Heizmann 84 1 0 18 Mar 2021
CheXseen: Unseen Disease Detection for Deep Learning Interpretation of Chest X-rays Siyu Shi Ishaan Malhi Ke M. Tran A. Ng Pranav Rajpurkar 97 4 0 08 Mar 2021
RotoGrad: Gradient Homogenization in Multitask LearningInternational Conference on Learning Representations (ICLR), 2021 Adrián Javaloy Isabel Valera 268 105 0 03 Mar 2021
Unbiased Sentence Encoder For Large-Scale Multi-lingual Search Engines Mahdi Hajiaghayi Monir Hajiaghayi Mark R. Bolin 74 0 0 01 Mar 2021