Understanding and Improving Information Transfer in Multi-Task Learning

International Conference on Learning Representations (ICLR), 2020

2 May 2020

Sen Wu

Hongyang R. Zhang

Christopher Ré

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)

Papers citing "Understanding and Improving Information Transfer in Multi-Task Learning"

50 / 109 papers shown

Title
Efficient Computation Sharing for Multi-Task Visual Scene UnderstandingIEEE International Conference on Computer Vision (ICCV), 2023 Sara Shoouri Mingyu Yang Zichen Fan Hun-Seok Kim MoE 149 5 0 16 Mar 2023
Provable Pathways: Learning Multiple Tasks over Multiple PathsAAAI Conference on Artificial Intelligence (AAAI), 2023 Yingcong Li Samet Oymak MoE 135 4 0 08 Mar 2023
Estimating Treatment Effects from Irregular Time Series Observations with Hidden ConfoundersAAAI Conference on Artificial Intelligence (AAAI), 2023 Defu Cao James Enouen Yujing Wang Xiangchen Song Chuizheng Meng Hao Niu Yan Liu CML 112 26 0 04 Mar 2023
PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding Zhangyang Gao Yuqi Hu Cheng Tan Stan Z. Li 196 15 0 14 Feb 2023
Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary DataNeural Information Processing Systems (NeurIPS), 2023 Alon Albalak Colin Raffel William Yang Wang 165 13 0 01 Feb 2023
Task-Adaptive Meta-Learning Framework for Advancing Spatial GeneralizabilityAAAI Conference on Artificial Intelligence (AAAI), 2022 Zhexiong Liu Licheng Liu Yiqun Xie Zhenong Jin X. Jia 113 12 0 10 Dec 2022
Fair Generative Models via Transfer LearningAAAI Conference on Artificial Intelligence (AAAI), 2022 Christopher T. H. Teo Milad Abdollahzadeh Ngai-Man Cheung 157 28 0 02 Dec 2022
GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization PerspectiveAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Linyi Yang Shuibai Zhang Libo Qin Yafu Li Yidong Wang Hanmeng Liu Yongfeng Zhang Xingxu Xie Yue Zhang ELM 409 91 0 15 Nov 2022
Task Compass: Scaling Multi-task Pre-training with Task PrefixConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Zhuosheng Zhang Shuohang Wang Yichong Xu Yuwei Fang Wenhao Yu Yang Liu Han Zhao Chenguang Zhu Michael Zeng SSL LRM 118 19 0 12 Oct 2022
A Kernel-Based View of Language Model Fine-TuningInternational Conference on Machine Learning (ICML), 2022 Sadhika Malladi Alexander Wettig Dingli Yu Danqi Chen Sanjeev Arora VLM 236 86 0 11 Oct 2022
Universal Prompt Tuning for Graph Neural NetworksNeural Information Processing Systems (NeurIPS), 2022 Taoran Fang Yunchao Zhang Yang Yang Chunping Wang Lei Chen 247 86 0 30 Sep 2022
On Transfer of Adversarial Robustness from Pretraining to Downstream TasksNeural Information Processing Systems (NeurIPS), 2022 Laura Fee Nern Harsh Raj Maurice Georgi Yash Sharma AAML 182 6 0 07 Aug 2022
Saliency-Regularized Deep Multi-Task LearningKnowledge Discovery and Data Mining (KDD), 2022 Guangji Bai Liang Zhao 120 12 0 03 Jul 2022
DNA: Proximal Policy Optimization with a Dual Network ArchitectureNeural Information Processing Systems (NeurIPS), 2022 Mathew H. Aitchison Penny Sweetser OffRL 80 6 0 20 Jun 2022
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale KnowledgeNeural Information Processing Systems (NeurIPS), 2022 Linxi Fan Guanzhi Wang Yunfan Jiang Ajay Mandlekar Yuncong Yang Haoyi Zhu Andrew Tang De-An Huang Yuke Zhu Anima Anandkumar LM&Ro 277 467 0 17 Jun 2022
Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense ReasoningNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 Yu Jin Kim Beong-woo Kwak Youngwook Kim Reinald Kim Amplayo Seung-won Hwang Jinyoung Yeo LRM 110 16 0 08 Jun 2022
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization GuaranteesInternational Conference on Machine Learning (ICML), 2022 Haotian Ju Dongyue Li Hongyang R. Zhang 242 34 0 06 Jun 2022
Compressed Hierarchical Representations for Multi-Task Learning and Task ClusteringIEEE International Joint Conference on Neural Network (IJCNN), 2022 João Machado de Freitas Sebastian Berg Bernhard C. Geiger Manfred Mücke 151 2 0 31 May 2022
InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction TuningConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Prakhar Gupta Cathy Jiao Yi-Ting Yeh Shikib Mehri M. Eskénazi Jeffrey P. Bigham ALM 208 53 0 25 May 2022
Improving Multi-Task Generalization via Regularizing Spurious CorrelationNeural Information Processing Systems (NeurIPS), 2022 Ziniu Hu Zhe Zhao Xinyang Yi Tiansheng Yao Lichan Hong Luke Huan Ed H. Chi OOD LRM 225 37 0 19 May 2022
XLTime: A Cross-Lingual Knowledge Transfer Framework for Temporal Expression Extraction Dongyuan Li William Groves T. K. Saha Joel R. Tetreault Alex Jaimes Hao Peng Philip S. Yu 77 16 0 03 May 2022
Jack and Masters of all Trades: One-Pass Learning Sets of Model Sets From Large Pre-Trained ModelsIEEE Computational Intelligence Magazine (IEEE CIM), 2022 Han Xiang Choong Yew-Soon Ong Abhishek Gupta Caishun Chen Ray Lim 96 7 0 02 May 2022
Control-Aware Prediction Objectives for Autonomous DrivingIEEE International Conference on Robotics and Automation (ICRA), 2022 R. McAllister Blake Wulfe Jean Mercat Logan Ellis Sergey Levine Adrien Gaidon 89 22 0 28 Apr 2022
KOBEST: Korean Balanced Evaluation of Significant TasksInternational Conference on Computational Linguistics (COLING), 2022 Dohyeong Kim Myeongjun Jang D. Kwon Eric Davis ALM 113 35 0 09 Apr 2022
Provable and Efficient Continual Representation Learning Yingcong Li Mingchen Li M. Salman Asif Samet Oymak CLL 162 16 0 03 Mar 2022
HyperPrompt: Prompt-based Task-Conditioning of TransformersInternational Conference on Machine Learning (ICML), 2022 Yun He H. Zheng Yi Tay Jai Gupta Yu Du ... Yaguang Li Zhaoji Chen Donald Metzler Heng-Tze Cheng Ed H. Chi LRM VLM 225 105 0 01 Mar 2022
Understanding Contrastive Learning Requires Incorporating Inductive BiasesInternational Conference on Machine Learning (ICML), 2022 Nikunj Saunshi Jordan T. Ash Surbhi Goel Dipendra Kumar Misra Cyril Zhang Sanjeev Arora Sham Kakade A. Krishnamurthy SSL 183 124 0 28 Feb 2022
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-DistributionInternational Conference on Learning Representations (ICLR), 2022 Ananya Kumar Aditi Raghunathan Robbie Jones Tengyu Ma Abigail Z. Jacobs OODD 251 801 0 21 Feb 2022
Adaptive and Robust Multi-Task LearningAnnals of Statistics (Ann. Stat.), 2022 Yaqi Duan Kaizheng Wang 299 36 0 10 Feb 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
GearNet: Stepwise Dual Learning for Weakly Supervised Domain AdaptationAAAI Conference on Artificial Intelligence (AAAI), 2022 Renchunzi Xie Jianguo Huang Lei Feng Bo An 156 12 0 16 Jan 2022
Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task Quan Feng Songcan Chen 127 5 0 07 Jan 2022
Analysis and Prediction of NLP Models Via Task Embeddings Damien Sileo Marie-Francine Moens 75 4 0 10 Dec 2021
Transfer Learning in Conversational Analysis through Reusing Preprocessing Data as Supervisors Joshua Y. Kim Tongliang Liu K. Yacef 117 0 0 02 Dec 2021
Improved Regularization and Robustness for Fine-tuning in Neural Networks Dongyue Li Hongyang R. Zhang NoLa 182 64 0 08 Nov 2021
Multi-Task Learning based Convolutional Models with Curriculum Learning for the Anisotropic Reynolds Stress Tensor in Turbulent Duct Flow Haitz Sáez de Ocáriz Borde David Sondak P. Protopapas AI4CE 120 3 0 30 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
Noise2Recon: Enabling Joint MRI Reconstruction and Denoising with Semi-Supervised and Self-Supervised Learning Arjun D Desai Batu Mehmet Ozturkler Christopher M. Sandino R. Boutin M. Willis S. Vasanawala B. Hargreaves Christopher Ré John M. Pauly Akshay S. Chaudhari 186 3 0 30 Sep 2021
On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation Dan Iter David Grangier 165 11 0 15 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
A Flexible Multi-Task Model for BERT Serving Tianwen Wei Jianwei Qi Shenghuang He 84 8 0 12 Jul 2021
Disentangling Transfer and Interference in Multi-Domain Learning Yipeng Zhang Tyler L. Hayes Christopher Kanan 208 3 0 02 Jul 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 100 12 0 21 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
Cross-Network Learning with Partially Aligned Graph Convolutional NetworksKnowledge Discovery and Data Mining (KDD), 2021 Meng Jiang GNN 85 12 0 03 Jun 2021
Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study D. Kollias V. Sharmanska Stefanos Zafeiriou CVBM 142 242 0 08 May 2021
CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Qinyuan Ye Bill Yuchen Lin Xiang Ren 457 190 0 18 Apr 2021
Embedding Adaptation is Still Needed for Few-Shot Learning Sébastien M. R. Arnold Fei Sha VLM 143 7 0 15 Apr 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
Comparing Deep Learning strategies for paired but unregistered multimodal segmentation of the liver in T1 and T2-weighted MRI V. Couteaux Mathilde Trintignac O. Nempont G. Pizaine A. Vlachomitrou P. Valette L. Milot Isabelle Bloch 111 3 0 18 Jan 2021