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 / 739 papers shown

Title
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 856 1 0 07 Mar 2025
Knowledge Retention for Continual Model-Based Reinforcement Learning Yixiang Sun Haotian Fu M. L. Littman George Konidaris OffRL CLL VLM 262 1 0 06 Mar 2025
An Information-theoretic Multi-task Representation Learning Framework for Natural Language UnderstandingAAAI Conference on Artificial Intelligence (AAAI), 2025 Dou Hu Lingwei Wei Wei Zhou Songlin Hu 190 1 0 06 Mar 2025
Continual Optimization with Symmetry Teleportation for Multi-Task Learning Zhipeng Zhou Ziqiao Meng Pengcheng Wu Peilin Zhao Chunyan Miao 127 0 0 06 Mar 2025
Gradient Deconfliction via Orthogonal Projections onto Subspaces For Multi-task LearningWeb Search and Data Mining (WSDM), 2025 Shijie Zhu Hui Zhao Tianshu Wu Pengjie Wang Hongbo Deng Jian Xu Bo Zheng 198 1 0 05 Mar 2025
Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Alessio Galatolo Zhenbang Dai Katie Winkle Meriem Beloucif 195 0 0 05 Mar 2025
DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal CyclesComputer Vision and Pattern Recognition (CVPR), 2025 Rui Zhao Weijia Mao Mike Zheng Shou 197 4 0 05 Mar 2025
Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization Aviv Shamsian E. Shaar Aviv Navon Gal Chechik Ethan Fetaya MU 212 0 0 04 Mar 2025
From Understanding the World to Intervening in It: A Unified Multi-Scale Framework for Embodied Cognition Maijunxian Wang 134 0 0 02 Mar 2025
Towards Understanding the Benefit of Multitask Representation Learning in Decision Process Rui Lu Yang Yue Andrew Zhao S. Du Gao Huang OffRL 186 1 0 01 Mar 2025
Joint Modeling in Recommendations: A Survey Xiangyu Zhao Yichao Wang Bo Chen Jingtong Gao Yuhao Wang Xiaopeng Li Pengyue Jia Qiang Liu Huifeng Guo Ruiming Tang 153 1 0 28 Feb 2025
Balanced Rate-Distortion Optimization in Learned Image CompressionComputer Vision and Pattern Recognition (CVPR), 2025 Yichi Zhang Z. Duan Yuning Huang Fengqing Zhu 192 2 0 27 Feb 2025
Gradient-Guided Annealing for Domain GeneralizationComputer Vision and Pattern Recognition (CVPR), 2025 Aristotelis Ballas Christos Diou OOD 1.0K 4 0 27 Feb 2025
Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks Luise Ge Michael Lanier Anindya Sarkar Bengisu Guresti Yevgeniy Vorobeychik Chongjie Zhang 274 1 0 26 Feb 2025
Directional Gradient Projection for Robust Fine-Tuning of Foundation ModelsInternational Conference on Learning Representations (ICLR), 2025 Chengyue Huang Junjiao Tian Brisa Maneechotesuwan Shivang Chopra Z. Kira 311 6 0 21 Feb 2025
Uncertain Multi-Objective Recommendation via Orthogonal Meta-Learning Enhanced Bayesian Optimization Hongxu Wang Zhu Sun Yingpeng Du Lu Zhang Tiantian He Yew-Soon Ong 149 1 0 18 Feb 2025
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent Junda Wu Yuxin Xiong Xintong Li Yu Xia Ruoyu Wang ... Sungchul Kim Ryan Rossi Lina Yao Jingbo Shang Julian McAuley CLL VLM 206 1 0 17 Feb 2025
MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models Zhen Zhang Yue Yang Kai Zhen Nathan Susanj Athanasios Mouchtaris Siegfried Kunzmann Zheng Zhang 282 2 0 17 Feb 2025
PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Zeman Li Yuan Deng Peilin Zhong Meisam Razaviyayn Vahab Mirrokni MoMe 337 1 0 10 Feb 2025
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic TransformationsComputer Vision and Pattern Recognition (CVPR), 2025 Krishna Sri Ipsit Mantri Carola-Bibiane Schönlieb Bruno Ribeiro Chaim Baskin Moshe Eliasof 285 5 0 09 Feb 2025
Skill Expansion and Composition in Parameter SpaceInternational Conference on Learning Representations (ICLR), 2025 Tenglong Liu Junjie Li Yinan Zheng Haoyi Niu Yixing Lan Xin Xu Xianyuan Zhan 241 6 0 09 Feb 2025
Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective Sizhuang He Ananyae Kumar Bhartari Bowen Li P. Perdikaris PINN 307 29 0 02 Feb 2025
Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Alexey Rukhovich Alexander Podolskiy Irina Piontkovskaya 175 1 0 28 Jan 2025
Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts Wenju Sun Qingyong Li Wen Wang Yangli-ao Geng Boyang Li 255 6 0 28 Jan 2025
E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion DetectionNeural Information Processing Systems (NeurIPS), 2024 Jiaqing Zhang Mingxiang Cao Weiying Xie Jie Lei Daixun Li Wenbo Huang Yunsong Li Xue Yang 249 23 0 28 Jan 2025
CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary Jiahang Tu Qian Feng Jiahua Dong Jiahua Dong Hanbin Zhao Chao Zhang Hui Qian DiffM 221 4 0 26 Jan 2025
Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination DynamicsAdaptive Agents and Multi-Agent Systems (AAMAS), 2025 S. Hazra P. Dasgupta Soumyajit Dey 172 0 0 21 Jan 2025
Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond Weiyu Chen Xiaoyuan Zhang Xiaoyuan Zhang Xi Lin Han Zhao Gang Qu James T. Kwok 288 15 0 19 Jan 2025
Optimizing Speech Multi-View Feature Fusion through Conditional ComputationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025 Weiqiao Shan Yuhao Zhang Yuchen Han Yangqiu Song X. Zhao Yongqian Li Hao Fei Hao Yang Tong Xiao Jingbo Zhu 93 0 0 14 Jan 2025
Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning Hanwen Zhong Jiaxin Chen Yutong Zhang Di Huang Yunhong Wang MoE 154 0 0 12 Jan 2025
Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic Yifei He Yuzheng Hu Yong Lin Tong Zhang Han Zhao FedML MoMe 211 29 0 08 Jan 2025
Generalized Task-Driven Medical Image Quality Enhancement with Gradient PromotionIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025 Dong Zhang Kwang-Ting Cheng MedIm 207 3 0 03 Jan 2025
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language TasksNeural Information Processing Systems (NeurIPS), 2024 Jiannan Wu Muyan Zhong Sen Xing Zeqiang Lai Zhaoyang Liu ... Lewei Lu Tong Lu Ping Luo Yu Qiao Jifeng Dai MLLM VLM LRM 527 99 0 03 Jan 2025
A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech TranslationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 Xiaoqian Liu Yangfan Du Jiadong Wang Yuan Ge Chen Xu Tong Xiao Guocheng Chen Jingbo Zhu 222 0 0 31 Dec 2024
Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning PerspectiveIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024 Yuanze Li Chun-Mei Feng Qilong Wang Guanglei Yang Wangmeng Zuo 104 0 0 27 Dec 2024
PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective OptimizationAAAI Conference on Artificial Intelligence (AAAI), 2024 Mingjing Xu Peizhong Ju Jia Liu Haibo Yang 202 5 0 14 Dec 2024
Nested Hash Layer: A Plug-and-play Module for Multiple-length Hash Code Learning Liyang He Yuren Zhang Rui Li Zhenya Huang Runze Wu Tong Xu 212 0 0 12 Dec 2024
Preventing Conflicting Gradients in Neural Marked Temporal Point Processes T. Bosser Souhaib Ben Taieb AI4TS 166 0 0 11 Dec 2024
FERERO: A Flexible Framework for Preference-Guided Multi-Objective LearningNeural Information Processing Systems (NeurIPS), 2024 Lisha Chen A. F. M. Saif Yanning Shen Tianyi Chen 165 3 0 02 Dec 2024
Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive GuidanceThe Web Conference (WWW), 2024 Zhe Wang Haozhu Wang Yanjun Qi OffRL 239 1 0 01 Dec 2024
MUNBa: Machine Unlearning via Nash Bargaining Jing Wu Mehrtash Harandi MU 392 7 0 23 Nov 2024
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with TransformersNeural Information Processing Systems (NeurIPS), 2024 Jake Grigsby Justin Sasek Samyak Parajuli Daniel Adebi Amy Zhang Yuke Zhu OffRL 162 12 0 17 Nov 2024
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant DeploymentNeural Information Processing Systems (NeurIPS), 2024 Y. Fu Zhongzhi Yu Junwei Li Jiayi Qian Yongan Zhang Xiangchi Yuan Dachuan Shi Roman Yakunin Y. Lin 164 7 0 15 Nov 2024
Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head Penghui Yang Chen-Chen Zong Sheng-Jun Huang Lei Feng Bo An 296 2 0 13 Nov 2024
UniGAD: Unifying Multi-level Graph Anomaly DetectionNeural Information Processing Systems (NeurIPS), 2024 Yiqing Lin Jianheng Tang Chenyi Zi Haihong Zhao Yuan Yao Jia Li 139 6 0 10 Nov 2024
Online Parallel Multi-Task Relationship Learning via Alternating Direction Method of Multipliers Ruiyu Li Peilin Zhao Guangxia Li Zhiqiang Xu Xuewei Li 74 0 0 09 Nov 2024
A Bayesian Approach to Data Point SelectionNeural Information Processing Systems (NeurIPS), 2024 Xinnuo Xu Minyoung Kim Royson Lee Brais Martínez Timothy M. Hospedales 145 1 0 06 Nov 2024
Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial TrainingEuropean Conference on Computer Vision (ECCV), 2024 Yuanqi Yao Gang Wu Kui Jiang Siao Liu Jian Kuai Xianming Liu Junjun Jiang MDE 150 6 0 04 Nov 2024
Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning Ziqing Fan Shengchao Hu Yuhang Zhou Li Shen Ya Zhang Yanfeng Wang Dacheng Tao OffRL 157 0 0 02 Nov 2024
Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Optimization Meitong Liu Xiaoyuan Zhang Chulin Xie Kate Donahue Han Zhao 199 4 0 29 Oct 2024