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 / 110 papers shown

Title
Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation Zhenshuo Zhang Minxuan Duan Youran Ye Hongyang R. Zhang OffRL 52 0 0 16 Nov 2025
Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning Pîrvu Mihai-Cristian Leordeanu Marius 90 1 0 11 Oct 2025
A Unified Multi-Task Learning Framework for Generative Auto-Bidding with Validation-Aligned Optimization Yiqin Lv Zhiyu Mou Miao Xu J. Chen Qi Wang ... Rongquan Bai Chuan Yu Jian Xu Bo Zheng Xiangyang Ji 28 0 0 09 Oct 2025
Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness Zihan Liang Ziwen Pan Ruoxuan Xiong CML 80 0 0 21 Sep 2025
Mutual Information Tracks Policy Coherence in Reinforcement Learning Cameron Reid Wael Hafez Amirhossein Nazeri 56 0 0 12 Sep 2025
Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation Ziniu Zhang Zhenshuo Zhang Dongyue Li Lu Wang Jennifer Dy Hongyang R. Zhang 64 1 0 27 Aug 2025
Adaptive Multi-task Learning for Multi-sector Portfolio Optimization Qingliang Fan Ruike Wu Yanrong Yang 84 0 0 22 Jul 2025
Generative or Discriminative? Revisiting Text Classification in the Era of Transformers Siva Rajesh Kasa Karan Gupta Sumegh Roychowdhury Ashutosh Kumar Yaswanth Biruduraju Santhosh Kumar Kasa Nikhil Pattisapu Arindam Bhattacharya Shailendra Agarwal Vijay huddar 127 2 0 13 Jun 2025
Efficient Ensemble for Fine-tuning Language Models on Multiple DatasetsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Dongyue Li Ziniu Zhang Lu Wang Hongyang R. Zhang 117 4 0 28 May 2025
Uniform Loss vs. Specialized Optimization: A Comparative Analysis in Multi-Task Learning Gabriel S. Gama Valdir Grassi Jr MoMe 225 0 0 15 May 2025
Efficient UAV Swarm-Based Multi-Task Federated Learning with Dynamic Task Knowledge Sharing Yubo Yang Tao Yang X. Wu Ziyu Guo Bo Hu 218 3 0 12 Mar 2025
Statistical Deficiency for Task Inclusion EstimationAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Loïc Fosse Frédéric Béchet Benoit Favre Géraldine Damnati Gwénolé Lecorvé Maxime Darrin Philippe Formont Pablo Piantanida 888 1 0 07 Mar 2025
Parameter-Efficient Interventions for Enhanced Model Merging Marcin Osial Daniel Marczak Bartosz Zieliñski MoMe 286 1 0 22 Dec 2024
USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness TaskInternational Workshop on Semantic Evaluation (SemEval), 2024 Jianjian Li Shengwei Liang Yong Liao Hongping Deng Haiyang Yu 262 2 0 28 Nov 2024
Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable InformationJournal of Biomedical Informatics (JBI), 2024 Yingya Li Timothy A. Miller Steven Bethard G. Savova 175 4 0 16 Oct 2024
Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer SamplesInternational Conference on Machine Learning (ICML), 2024 Thomas T. Zhang Bruce D. Lee Ingvar M. Ziemann George J. Pappas Nikolai Matni CML OOD 257 2 0 15 Oct 2024
Distilling Invariant Representations with Dual Augmentation Nikolaos Giakoumoglou Tania Stathaki 166 0 0 12 Oct 2024
Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation ApproachConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 Dongyue Li Ziniu Zhang Lu Wang Hongyang R. Zhang 239 3 0 28 Sep 2024
Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning Siqi Sun Korin Richmond 190 0 0 15 Sep 2024
Scalable Multitask Learning Using Gradient-based Estimation of Task AffinityKnowledge Discovery and Data Mining (KDD), 2024 Dongyue Li Aneesh Sharma Hongyang R. Zhang 238 8 0 09 Sep 2024
Theoretical Insights into Overparameterized Models in Multi-Task and Replay-Based Continual Learning Mohammadamin Banayeeanzade Mahdi Soltanolkotabi Mohammad Rostami CLL LRM 457 5 0 29 Aug 2024
Diffusion Models for Multi-Task Generative Modeling Changyou Chen Han Ding Bunyamin Sisman Yi Tian Xu Ouye Xie Benjamin Z. Yao Son Dinh Tran Belinda Zeng DiffM 153 7 0 24 Jul 2024
$α$ VIL: Learning to Leverage Auxiliary Tasks for Multitask Learning Rafael Kourdis Gabriel Gordon-Hall P. Gorinski 77 0 0 13 May 2024
Condition-Aware Neural Network for Controlled Image Generation Han Cai Zhekai Zhang Zhuoyang Zhang Qinsheng Zhang Ming-Yu Liu Song Han DiffM 116 15 0 01 Apr 2024
A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives Simone Alberto Peirone Francesca Pistilli A. Alliegro Giuseppe Averta EgoV 214 7 0 05 Mar 2024
Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks Tianyu Fan Lirong Wu Yufei Huang Haitao Lin Cheng Tan Zhangyang Gao Stan Z. Li 186 3 0 03 Mar 2024
HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization Guanglin Zhou Zhongyi Han Shiming Chen Erdun Gao Liming Zhu Tongliang Liu Lina Yao Kun Zhang 167 5 0 18 Jan 2024
Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & BeyondAAAI Conference on Artificial Intelligence (AAAI), 2024 D. Kollias V. Sharmanska Stefanos Zafeiriou CVBM 305 62 0 02 Jan 2024
MultiGPrompt for Multi-Task Pre-Training and Prompting on GraphsThe Web Conference (WWW), 2023 Xingtong Yu Chang Zhou Yuan Fang Xinming Zhang 440 52 0 28 Nov 2023
One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning Doyoung Kim Susik Yoon Dongmin Park Youngjun Lee Hwanjun Song Jihwan Bang Jae-Gil Lee VLM 199 4 0 18 Nov 2023
An Eye on Clinical BERT: Investigating Language Model Generalization for Diabetic Eye Disease Phenotyping Keith Harrigian Tina Tang Anthony Gonzales Cindy X. Cai Mark Dredze VLM 124 2 0 15 Nov 2023
Contrastive Modules with Temporal Attention for Multi-Task Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2023 Siming Lan Rui Zhang Qi Yi Jiaming Guo Shaohui Peng ... Zidong Du Xingui Hu Xishan Zhang Ling Li Yunji Chen 156 14 0 02 Nov 2023
Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident AnalysisNeural Information Processing Systems (NeurIPS), 2023 Abhinav Nippani Dongyue Li Haotian Ju Haris N. Koutsopoulos Hongyang R. Zhang GNN 317 16 0 31 Oct 2023
Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task LearningConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Chong Li Shaonan Wang Yunhao Zhang Jiajun Zhang Chengqing Zong 156 7 0 16 Oct 2023
AdaMerging: Adaptive Model Merging for Multi-Task LearningInternational Conference on Learning Representations (ICLR), 2023 Enneng Yang Zhenyi Wang Li Shen Shiwei Liu Guibing Guo Xingwei Wang Dacheng Tao MoMe 220 168 0 04 Oct 2023
LoRA ensembles for large language model fine-tuning Xi Wang Laurence Aitchison Maja Rudolph UQCV 317 49 0 29 Sep 2023
Task-Based MoE for Multitask Multilingual Machine Translation Hai Pham Young Jin Kim Subhabrata Mukherjee David P. Woodruff Barnabás Póczós Hany Awadalla MoE 133 7 0 30 Aug 2023
Revisiting Scalarization in Multi-Task Learning: A Theoretical PerspectiveNeural Information Processing Systems (NeurIPS), 2023 Yuzheng Hu Ruicheng Xian Qilong Wu Qiuling Fan Lang Yin Han Zhao 189 60 0 27 Aug 2023
Less is More -- Towards parsimonious multi-task models using structured sparsity Richa Upadhyay Ronald Phlypo Rajkumar Saini Marcus Liwicki MoE 182 3 0 23 Aug 2023
Privileged Anatomical and Protocol Discrimination in Trackerless 3D Ultrasound Reconstruction Qi Li Ziyi Shen Qian Li D. Barratt T. Dowrick Matthew J. Clarkson Tom Vercauteren Yipeng Hu 72 1 0 20 Aug 2023
Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Survey Lovre Torbarina Tin Ferkovic Lukasz Roguski Velimir Mihelčić Bruno Šarlija Z. Kraljevic 171 5 0 16 Aug 2023
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable PrimitivesComputer Vision and Pattern Recognition (CVPR), 2023 Chuntao Ding Zhichao Lu Shangguang Wang Ran Cheng Vishnu Boddeti MoMe 131 24 0 03 Aug 2023
Provable Multi-Task Representation Learning by Two-Layer ReLU Neural NetworksInternational Conference on Machine Learning (ICML), 2023 Liam Collins Hamed Hassani Mahdi Soltanolkotabi Aryan Mokhtari Sanjay Shakkottai 331 11 0 13 Jul 2023
Mitigating Negative Transfer with Task Awareness for Sexism, Hate Speech, and Toxic Language DetectionIEEE International Joint Conference on Neural Network (IJCNN), 2023 Angel Felipe Magnossão de Paula Paolo Rosso Damiano Spina 137 5 0 07 Jul 2023
STG-MTL: Scalable Task Grouping for Multi-Task Learning Using Data Map Ammar Sherif Abubakar Abid M. Elattar Mohamed ElHelw 219 5 0 07 Jul 2023
Boosting Multitask Learning on Graphs through Higher-Order Task AffinitiesKnowledge Discovery and Data Mining (KDD), 2023 Dongyue Li Haotian Ju Aneesh Sharma Hongyang R. Zhang 282 12 0 24 Jun 2023
A Universal Semantic-Geometric Representation for Robotic ManipulationConference on Robot Learning (CoRL), 2023 Tong Zhang Yingdong Hu Hanchen Cui Hang Zhao Yang Gao 196 24 0 18 Jun 2023
Addressing Negative Transfer in Diffusion ModelsNeural Information Processing Systems (NeurIPS), 2023 Hyojun Go Jinyoung Kim Yunsung Lee Seunghyun Lee Shinhyeok Oh Hyeongdon Moon Seungtaek Choi DiffM VLM 376 28 0 01 Jun 2023
Learning to Generalize for Cross-domain QAAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Yingjie Niu Linyi Yang Ruihai Dong Yue Zhang 188 6 0 14 May 2023
Identification of Negative Transfers in Multitask Learning Using Surrogate Models Dongyue Li Huy Le Nguyen Hongyang R. Zhang 167 15 0 25 Mar 2023