Dimensional reduction~(DR) maps high-dimensional data into a lower dimensions latent space with minimized defined optimization objectives. The DR method usually falls into feature selection~(FS) and feature projection~(FP). FS focuses on selecting a critical subset of dimensions but risks destroying the data distribution (structure). On the other hand, FP combines all the input features into lower dimensions space, aiming to maintain the data structure; but lacks interpretability and sparsity. FS and FP are traditionally incompatible categories; thus, they have not been unified into an amicable framework. We propose that the ideal DR approach combines both FS and FP into a unified end-to-end manifold learning framework, simultaneously performing fundamental feature discovery while maintaining the intrinsic relationships between data samples in the latent space. In this work, we develop a unified framework, Unified Dimensional Reduction Neural-network~(UDRN), that integrates FS and FP in a compatible, end-to-end way. We improve the neural network structure by implementing FS and FP tasks separately using two stacked sub-networks. In addition, we designed data augmentation of the DR process to improve the generalization ability of the method when dealing with extensive feature datasets and designed loss functions that can cooperate with the data augmentation. Extensive experimental results on four image and four biological datasets, including very high-dimensional data, demonstrate the advantages of DRN over existing methods~(FS, FP, and FS\&FP pipeline), especially in downstream tasks such as classification and visualization.
Near-Linear Time Projection onto the $\ell_{1,\infty}$ Ball; Application to Sparse Autoencoders
Université Côte d’Azur（蔚蓝海岸大学）；CNRS（法国国家科学研究中心）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；SDAIA-KAUST AI（SDAIA-KAUST人工智能中心）
Shanghai Key Laboratory of Automobile Intelligent Network Interaction Chip and System, School of Microelectronics, Shanghai University（上海汽车智能网络交互芯片与系统重点实验室，微电子学院，上海大学）；School of Mechatronic Engineering and Automation, Shanghai University（机械电子工程与自动化学院，上海大学）；School of Intelligent Systems Engineering, Sun Yat-sen University（智能系统工程学院，中山大学）
Selection of CMIP6 Models for Regional Precipitation Projection and Climate Change Assessment in the Jhelum and Chenab River Basins
Department of Computer Science, University of Évora（埃夫拉尔大学计算机科学系）；MED—Mediterranean Institute for Agriculture, Environment and Development & CHANGE—Global Change and Sustainability Institute, Institute for Advanced Studies and Research, University of Évora（地中海农业、环境与发展研究所及全球变化与可持续性研究所，埃夫拉尔大学高级研究学院）；NUST Institute of Civil Engineering (NICE), School of Civil and Environmental Engineering (SCEE), National University of Sciences and Technology (NUST)（国家科技大学土木工程研究所（NICE）、土木与环境工程学院（SCEE））；Institute of Geographical Information Systems (IGIS), School of Civil and Environmental Engineering (SCEE), National University of Sciences and Technology (NUST)（地理信息系统研究所（IGIS）、土木与环境工程学院（SCEE），国家科技大学）；IMT Atlantique, Lab-STICC UMR CNRS 6285（IMT Atlantic、Lab-STICC UMR CNRS 6285）
SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科学与技术大学计算机科学与工程系）；Department of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程系）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）；Platform and Content Group, Tencent（腾讯平台与内容组）；Chinese Medicine Guangdong Laboratory（广东中医实验室）
Task-based Generation of Optimized Projection Sets using Differentiable Ranking
Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Fraunhofer Development Center X-Ray Technology EZRT（弗劳恩霍夫X射线技术发展中心（EZRT））；Johns Hopkins University（约翰斯·霍普金斯大学）
From STLS to Projection-based Dictionary Selection in Sparse Regression for System Identification
AI Institute in Dynamic Systems, Department of Mechanical Engineering, University of Washington（动态系统人工智能研究所，机械工程系，华盛顿大学）；Department of Mechanical Engineering, University of Hawai‘i at Mānoa（机械工程系，夏威夷大学马诺阿分校）；Departamento de Matemática e Computação, Faculdade de Ciências e Tecnologia, Universidade Estadual Paulista “Júlio de Mesquita Filho”（数学与计算系，科技学院，保罗斯州立大学“朱利奥·梅斯奎塔·弗洛雷斯”分校）
