v1v2 (latest)

Adapting Auxiliary Losses Using Gradient Similarity

5 December 2018

Yunshu Du

Wojciech M. Czarnecki

Siddhant M. Jayakumar

Mehrdad Farajtabar

Razvan Pascanu

Balaji Lakshminarayanan

ArXiv (abs)PDF HTML

Papers citing "Adapting Auxiliary Losses Using Gradient Similarity"

50 / 100 papers shown

Title
Auto-Lambda: Disentangling Dynamic Task Relationships Shikun Liu Stephen James Andrew J. Davison Edward Johns 114 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 96 154 0 02 Feb 2022
Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments A. Iyer Karan Grewal Akash Velu Lucas O. Souza Jérémy Forest Subutai Ahmad AI4CE 103 45 0 31 Dec 2021
Auxiliary Loss Reweighting for Image Inpainting Siqi Hui Sanping Zhou Ye Deng Wenli Huang Jinjun Wang 67 1 0 14 Nov 2021
Self-Supervised Knowledge Transfer via Loosely Supervised Auxiliary Tasks Seungbum Hong Jihun Yoon Junmo Kim Min-Kook Choi SSL 23 1 0 25 Oct 2021
Learning Multi-Objective Curricula for Robotic Policy Learning Jikun Kang Miao Liu Abhinav Gupta C. Pal Xue Liu Jie Fu 67 5 0 06 Oct 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 73 60 0 14 Sep 2021
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization Alexandre Ramé Corentin Dancette Matthieu Cord OOD 139 210 0 07 Sep 2021
Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral Lucio Dery Yann N. Dauphin David Grangier MoMe 71 29 0 25 Aug 2021
Adaptive Transfer Learning on Graph Neural Networks Xueting Han Zhenhuan Huang Bang An Jing Bai 115 57 0 19 Jul 2021
Multiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification Talha Qaiser S. Winzeck Theodore Barfoot T. Barwick S. Doran ... N. Tunariu D. Koh C. Messiou A. Rockall Ben Glocker 60 9 0 16 Jul 2021
Continual World: A Robotic Benchmark For Continual Reinforcement Learning Maciej Wołczyk Michal Zajkac Razvan Pascanu Lukasz Kuciñski Piotr Milo's CLL OffRL 79 98 0 23 May 2021
Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization Damien Teney Ehsan Abbasnejad Simon Lucey Anton Van Den Hengel 113 90 0 12 May 2021
ImageNet-21K Pretraining for the Masses T. Ridnik Emanuel Ben-Baruch Asaf Noy Lihi Zelnik-Manor SSeg VLM CLIP 341 716 0 22 Apr 2021
Spectral Reconstruction and Disparity from Spatio-Spectrally Coded Light Fields via Multi-Task Deep Learning Maximilian Schambach Jiayang Shi M. Heizmann 23 1 0 18 Mar 2021
On The Effect of Auxiliary Tasks on Representation Dynamics Clare Lyle Mark Rowland Georg Ostrovski Will Dabney 76 70 0 25 Feb 2021
Multi-Task Reinforcement Learning with Context-based Representations Shagun Sodhani Amy Zhang Joelle Pineau 98 191 0 11 Feb 2021
Improving RNN Transducer Based ASR with Auxiliary Tasks Chunxi Liu Frank Zhang Duc Le Suyoun Kim Yatharth Saraf Geoffrey Zweig 85 49 0 05 Nov 2020
Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Models Saurabh Kataria Jesús Villalba Najim Dehak VLM SSL 66 34 0 22 Oct 2020
Auxiliary Task Reweighting for Minimum-data Learning Baifeng Shi Judy Hoffman Kate Saenko Trevor Darrell Huijuan Xu MoMe 65 33 0 16 Oct 2020
Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models Zirui Wang Yulia Tsvetkov Orhan Firat Yuan Cao 79 202 0 12 Oct 2020
Multi-Task Learning with Deep Neural Networks: A Survey M. Crawshaw CVBM 217 626 0 10 Sep 2020
Multi-Loss Weighting with Coefficient of Variations R. Groenendijk Sezer Karaoglu Theo Gevers Thomas Mensink 146 55 0 03 Sep 2020
Learning explanations that are hard to vary Giambattista Parascandolo Alexander Neitz Antonio Orvieto Luigi Gresele Bernhard Schölkopf FAtt 86 187 0 01 Sep 2020
HydaLearn: Highly Dynamic Task Weighting for Multi-task Learning with Auxiliary Tasks Sam Verboven M. H. Chaudhary Jeroen Berrevoets Wouter Verbeke 46 7 0 26 Aug 2020
Training Multimodal Systems for Classification with Multiple Objectives Jason Armitage Shramana Thakur Rishi Tripathi Jens Lehmann M. Maleshkova 43 1 0 26 Aug 2020
Compact Speaker Embedding: lrx-vector Munir Georges Jonathan Huang Tobias Bocklet 24 11 0 11 Aug 2020
Knowledge Distillation for Multi-task Learning Weihong Li Hakan Bilen MoMe 59 73 0 14 Jul 2020
Towards a practical measure of interference for reinforcement learning Vincent Liu Adam White Hengshuai Yao Martha White 39 5 0 07 Jul 2020
A Brief Review of Deep Multi-task Learning and Auxiliary Task Learning Partoo Vafaeikia Khashayar Namdar Farzad Khalvati MoMe 51 44 0 02 Jul 2020
Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning Lionel Blondé Pablo Strasser Alexandros Kalousis 76 22 0 28 Jun 2020
Auxiliary Learning by Implicit Differentiation Aviv Navon Idan Achituve Haggai Maron Gal Chechik Ethan Fetaya 87 59 0 22 Jun 2020
Multi-Task Learning in Histo-pathology for Widely Generalizable Model Jevgenij Gamper Navid Alemi Koohbanani Nasir M. Rajpoot 52 7 0 09 May 2020
Finding the Optimal Network Depth in Classification Tasks Bartosz Wójcik Maciej Wołczyk Klaudia Bałazy Jacek Tabor 16 0 0 17 Apr 2020
Multi-Task Reinforcement Learning with Soft Modularization Ruihan Yang Huazhe Xu Yi Wu Xiaolong Wang 69 185 0 30 Mar 2020
Fine-grained Species Recognition with Privileged Pooling: Better Sample Efficiency Through Supervised Attention Andrés C. Rodríguez Stefano Dáronco Konrad Schindler Jan Dirk Wegner 21 4 0 20 Mar 2020
Gradient Surgery for Multi-Task Learning Tianhe Yu Saurabh Kumar Abhishek Gupta Sergey Levine Karol Hausman Chelsea Finn 197 1,232 0 19 Jan 2020
Regularizing Deep Multi-Task Networks using Orthogonal Gradients Mihai Suteu Yike Guo 73 59 0 14 Dec 2019
Optimizing Data Usage via Differentiable Rewards Xinyi Wang Hieu H. Pham Paul Michel Antonios Anastasopoulos J. Carbonell Graham Neubig 90 62 0 22 Nov 2019
Generalization in multitask deep neural classifiers: a statistical physics approach Tyler Lee A. Ndirango AI4CE 140 20 0 30 Oct 2019
MERL: Multi-Head Reinforcement Learning Yannis Flet-Berliac Philippe Preux OffRL 122 13 0 26 Sep 2019
Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning Bilal Kartal Pablo Hernandez-Leal Matthew E. Taylor 168 29 0 24 Jul 2019
Ray Interference: a Source of Plateaus in Deep Reinforcement Learning Tom Schaul Diana Borsa Joseph Modayil Razvan Pascanu 72 63 0 25 Apr 2019
Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning G. V. D. L. Cruz Yunshu Du Matthew E. Taylor OffRL 41 4 0 03 Apr 2019
Meta-Curvature Eunbyung Park Junier B. Oliva BDL 78 124 0 09 Feb 2019
Semi-Supervised Learning by Label Gradient Alignment Jacob Jackson John Schulman 94 20 0 06 Feb 2019
Improving Adversarial Robustness of Ensembles with Diversity Training Sanjay Kariyappa Moinuddin K. Qureshi AAML FedML 79 137 0 28 Jan 2019
Self-Supervised Generalisation with Meta Auxiliary Learning Shikun Liu Andrew J. Davison Edward Johns SSL OOD 73 163 0 25 Jan 2019
Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning G. V. D. L. Cruz Yunshu Du Matthew E. Taylor OffRL 43 26 0 21 Dec 2018
A Survey and Critique of Multiagent Deep Reinforcement Learning Pablo Hernandez-Leal Bilal Kartal Matthew E. Taylor OffRL 119 568 0 12 Oct 2018