Input Guided Multiple Deconstruction Single Reconstruction neural network models for Matrix Factorization
Indian Statistical Institute(印度统计研究所);Institute of Data Engineering, Analytics and Science Foundation, Technology Innovation Hub, Indian Statistical Institute(印度统计研究所数据工程、分析与科学基金会技术创新中心)
Referring back to the original text in the course of hierarchical learning is a common human trait that ensures the right direction of learning. The models developed based on the concept of Non-negative Matrix Factorization (NMF), in this paper are inspired by this idea. They aim to deal with high-dimensional data by discovering its low rank approximation by determining a unique pair of factor matrices. The model, named Input Guided Multiple Deconstruction Single Reconstruction neural network for Non-negative Matrix Factorization (IG-MDSR-NMF), ensures the non-negativity constraints of both factors. Whereas Input Guided Multiple Deconstruction Single Reconstruction neural network for Relaxed Non-negative Matrix Factorization (IG-MDSR-RNMF) introduces a novel idea of factorization with only the basis matrix adhering to the non-negativity criteria. This relaxed version helps the model to learn more enriched low dimensional embedding of the original data matrix. The competency of preserving the local structure of data in its low rank embedding produced by both the models has been appropriately verified. The superiority of low dimensional embedding over that of the original data justifying the need for dimension reduction has been established. The primacy of both the models has also been validated by comparing their performances separately with that of nine other established dimension reduction algorithms on five popular datasets. Moreover, computational complexity of the models and convergence analysis have also been presented testifying to the supremacy of the models.
FSRF: Factorization-guided Semantic Recovery for Incomplete Multimodal Sentiment Analysis
School of Future Science and Engineering, Soochow University(苏州大学未来科学与工程学院);School of Advanced Manufacturing Engineering, Hefei University(合肥大学先进制造工程学院);College of Global Talents, BITZH, Beijing Institute of Technology(北京理工大学珠海学院全球人才学院);Academy for Engineering and Technology, Fudan University(复旦大学工程与技术学院)
School of Automation, Chongqing University of Posts and Telecommunications(重庆邮电大学自动化学院);College of Computer and Information Science, School of Software, Southwest University(西南大学计算机与信息科学学院、软件学院)
Finite-Sample Approximation of Hessian-Guided Perturbed Wasserstein Gradient Flows
The University of Tokyo(东京大学);Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局);Nanyang Technological University(南洋理工大学);RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能研究中心)
Boosting Factorization Machines via Saliency-Guided Mixup
University of Science and Technology of China(中国科学技术大学);University of Arizona(亚利桑那大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);JD Explore Academy(京东探索研究院);University of Sydney(悉尼大学)
Graph-based Clustering Revisited: A Relaxation of Kernel $k$-Means Perspective
School of Computer Science and Engineering(计算机科学与工程学院);Division of Computer Science and Engineering(计算机科学与工程系);Yam Pak Charitable Foundation School of Computing and Information Sciences(Yam Pak慈善基金会计算与信息科学学院);Department of Computer Science(计算机科学系)
本文提出 LoRD 和 B-LoRD 两种低秩双随机聚类模型,仅松弛正交约束并引入块对角正则化,通过将非凸约束转化为线性凸约束,实现全局收敛的投影梯度下降优化,显著提升聚类性能。
Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments
Center for Advanced Intelligence Project (AIP), RIKEN(理化学研究所先进智能项目中心);Graduate School of Informatics, Kyoto University(京都大学信息学研究科);National Institute of Advanced Industrial Science and Technology (AIST)(日本产业技术综合研究所);LTCI, Télécom Paris, Institut Polytechnique de Paris(巴黎理工学院巴黎电信学院信息处理与通信实验室)