Fine-tuning the pre-trained model with active learning holds promise for reducing annotation costs. However, this combination introduces significant computational costs, particularly with the growing scale of pre-trained models. Recent research has proposed proxy-based active learning, which pre-computes features to reduce computational costs. Yet, this approach often incurs a significant loss in active learning performance, sometimes outweighing the computational cost savings. This paper demonstrates that not all sample selection differences result in performance degradation. Furthermore, we show that suitable training methods can mitigate the decline of active learning performance caused by certain selection discrepancies. Building upon detailed analysis, we propose a novel method, aligned selection via proxy, which improves proxy-based active learning performance by updating pre-computed features and selecting a proper training method. Extensive experiments validate that our method improves the total cost of efficient active learning while maintaining computational efficiency. The code is available at \url{https://github.com/ZiTingW/asvp}.
Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting
Washington State University(华盛顿州立大学);National University of Singapore(新加坡国立大学);National Institute of Advanced Industrial Science and Technology(国家先进工业科学与技术研究院);Hanoi University of Science and Technology(河内科学技术大学)
Rethinking LoRA for Data Heterogeneous Federated Learning: Subspace and State Alignment
College of Computing and Data Science, Nanyang Technological University, Singapore.(南洋理工大学计算机与数据科学学院);Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada.(不列颠哥伦比亚大学电子与计算机工程系);Vector Institute, Canada(加拿大向量研究所);The Hong Kong Polytechnic University(香港理工大学)
From Coefficients to Directions: Rethinking Model Merging with Directional Alignment
University of Oxford(牛津大学);Tsinghua University(清华大学);Nanyang Technological University(南洋理工大学);East China Normal University(华东师范大学);RIKEN(日本研究机构);The University of Tokyo(东京大学);Southern University of Science and Technology(南方科技大学)
Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
University of Science and Technology of China(中国科学技术大学);Deep Space Exploration Laboratory(深空探测实验室);Institute for Advanced Algorithms Research(先进算法研究院);Sangfor Technologies Inc.(深信服科技股份有限公司);Research Institute of China Telecom(中国电信研究院)
BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series
College of Computer Science, Nankai University, Tianjin, China(南开大学计算机科学学院);College of Cyber Science, Tianjin Key Laboratory of Interventional Brain-Computer Interface(天津介入脑机接口与智能康复重点实验室);Intelligent Rehabilitation, Key Lab of Data(智能康复,数据实验室);Intelligent System Security, Frontiers Science Center for New Organic Matter, Nankai University, Tianjin, China(智能系统安全,新有机物前沿科学中心,南开大学,天津,中国)
From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University(虚拟现实技术与系统国家重点实验室,计算机科学与工程学院,北京航空航天大学);Zhongguancun Laboratory(中关村实验室);Center for AI Business Innovation, Department of Management Science and Systems, School of Management, University at Buffalo(人工智能商业创新中心,管理科学与系统系,布法罗大学)
Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety
Wroclaw University of Science and Technology (WUST)(沃拉布大学科学与技术学院);National Research Institute (NASK)(国家研究 institute);Institute of Computer Science, Polish Academy of Sciences (IPI PAN)(波兰科学院计算机科学研究所)
Rethinking Flexible Graph Similarity Computation: One-step Alignment with Global Guidance
College of Computer Science and Technology(计算机科学与技术学院);National University of Defense Technology(国防科技大学);Beihang University(北航);Information Support Force Engineering University(信息支援工程大学)
Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment
Zhejiang University(浙江大学);The University of Manchester(曼彻斯特大学);University of Oxford(牛津大学);The University of Edinburgh(爱丁堡大学);Tsinghua University(清华大学);Donghai laboratory(东海实验室)
The Umwelt Representation Hypothesis: Rethinking Universality
Institute of Cognitive Science, University of Osnabrück(奥尔登堡大学认知科学研究所);Department of Psychology and Education, Freie Universität Berlin(柏林自由大学心理学与教育系);Bernstein Center for Computational Neuroscience, Berlin(柏林计算神经科学中心)
Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests
Department of Computer Science, Iowa State University(计算机科学系,爱荷华州立大学);Department of Civil, Construction & Environmental Engineering, Iowa State University(土木、建设与环境工程系,爱荷华州立大学)
Beyond local reconstruction: Geometry-preserving output alignment for binary LLM quantization
Department of Data Science and AI(数据科学与人工智能系);Monash University(墨尔本大学);Centre for Vision, Speech and Signal Processing(视觉、语音和信号处理中心);University of Surrey(萨里大学)
Omnimodal Dataset Distillation via High-order Proxy Alignment
University of Science and Technology of China(中国科学技术大学);Xidian University(西安电子科技大学);National University of Singapore(新加坡国立大学);The University of Sydney(悉尼大学)