Multi-task learning enables the acquisition of task-generic knowledge by training multiple tasks within a unified architecture. However, training all tasks together in a single architecture can lead to performance degradation, known as negative transfer, which is a main concern in multi-task learning. Previous works have addressed this issue by optimizing the multi-task network through gradient manipulation or weighted loss adjustments. However, their optimization strategy focuses on addressing task imbalance in shared parameters, neglecting the learning of task-specific parameters. As a result, they show limitations in mitigating negative transfer, since the learning of shared space and task-specific information influences each other during optimization. To address this, we propose a different approach to enhance multi-task performance by selectively grouping tasks and updating them for each batch during optimization. We introduce an algorithm that adaptively determines how to effectively group tasks and update them during the learning process. To track inter-task relations and optimize multi-task networks simultaneously, we propose proximal inter-task affinity, which can be measured during the optimization process. We provide a theoretical analysis on how dividing tasks into multiple groups and updating them sequentially significantly affects multi-task performance by enhancing the learning of task-specific parameters. Our methods substantially outperform previous multi-task optimization approaches and are scalable to different architectures and various numbers of tasks.
MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Shenzhen University of Advanced Technology(深圳理工大学);Pengcheng Laboratory(鹏城实验室);University of Chinese Academy of Sciences(中国科学院大学)
College of Electric and Information, Northeast Agricultural University(东北农业大学电气与信息学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning
School of Engineering, Institute of Science Tokyo, Japan(东京科学研究院工程学院);College of Control Science and Engineering, Zhejiang University, China(浙江大学控制科学与工程学院);Department of Electrical and Computer Engineering, National University of Singapore, Singapore(新加坡国立大学电子与计算机工程系)
MiLoop: Selective Memory Propagation for Neural Combinatorial Optimization
Southern University of Science and Technology(南方科技大学);Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology(广东省全驱系统控制理论与技术重点实验室);Pengcheng Laboratory(鹏城实验室)
Accelerating Neural Network Training with Distributed Asynchronous and Selective Optimization (DASO)
Steinbuch Centre for Computing (SCC)(施泰因布赫计算中心(SCC));Karlsruhe Institute of Technology (KIT)(卡尔斯鲁厄理工学院(KIT));Institute for Software Technology (SC)(软件技术研究所(SC));German Aerospace Center (DLF)(德国航空航天中心(DLF))
Snowball: A Scalable All-to-All Ising Machine with Dual-Mode Markov Chain Monte Carlo Spin Selection and Asynchronous Spin Updates for Fast Combinatorial Optimization
Selective Preference Optimization via Token-Level Reward Function Estimation
National Centre for Text Mining, The University of Manchester(曼彻斯特大学文本挖掘中心);School of Artificial Intelligence, Wuhan University(武汉大学人工智能学院);Center for Language and Information Research, Wuhan University(武汉大学语言与信息研究中心);The Fin AI(Fin AI公司);Baidu Inc.(百度公司);Archimedes Research(阿基米德研究)
SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring
Institute of Industrial Automation and Software Engineering, University of Stuttgart(斯图加特大学工业自动化与软件工程研究所);Eindhoven University of Technology (TU/e)(埃因霍温理工大学)
Learning When to Trust via Selective Context Preference Optimization
Duke University(杜克大学);National University of Singapore(新加坡国立大学);UC Berkeley(加州大学伯克利分校);UC Irvine(加州大学欧文分校);Northeastern University(东北大学);Nanyang Technological University(南洋理工大学)
Investigating layer-selective transfer learning of QAOA parameters for Max-Cut problem
Department of Engineering, University Pompeu Fabra(工程系,庞贝法布拉大学);Department of Physics and Astronomy, University of Florence(物理与天文学系,佛罗伦萨大学);QUANTIC, Barcelona Supercomputing Center(QUANTIC,巴塞罗那超级计算中心);Institute for Cross-Disciplinary Physics and Complex Systems (IFISC) UIB-CSIC(跨学科物理与复杂系统研究所(IFISC) UIB-CSIC);European Laboratory for Non-Linear Spectroscopy (LENS), University of Florence(非线性光谱欧洲实验室(LENS),佛罗伦萨大学)
LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Mechanical Engineering, Shanghai Jiao Tong University(上海交通大学机械工程学院);Institute for Advanced Study in Mathematics, Harbin Institute of Technology(哈尔滨工业大学数学研究所);School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院);School of Automation, Central South University(中南大学自动化学院);College of New Energy and Materials, China University of Petroleum, Beijing(中国石油大学(北京)新能源与材料学院);College of Carbon Neutrality Future Technology, China University of Petroleum, Beijing(中国石油大学(北京)碳中和未来技术学院);DeepVerse PTE. LTD.