arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.13449cs.LGcs.AI
收藏

输入引导的多重解构单重建神经网络模型用于矩阵分解

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)

Prasun Dutta, Rajat K. De

AI总结:

本文提出两种基于非负矩阵分解的神经网络模型(IG-MDSR-NMF和IG-MDSR-RNMF),通过输入引导的多重解构单重建实现低秩嵌入,在保持局部结构的同时优于九种算法,验证了降维的有效性。

摘要:

在分层学习过程中回顾原始文本是人类的一种常见特性,它确保了学习方向的正确性。本文基于非负矩阵分解(NMF)概念开发的模型正是受到这一思想的启发。这些模型旨在通过确定一对唯一的因子矩阵来发现高维数据的低秩近似,从而处理高维数据。名为输入引导的多重解构单重建神经网络用于非负矩阵分解(IG-MDSR-NMF)的模型确保了两种因子的非负性约束。而输入引导的多重解构单重建神经网络用于松弛非负矩阵分解(IG-MDSR-RNMF)则引入了一种新颖的分解思想,仅要求基矩阵满足非负性准则。这种松弛版本有助于模型学习原始数据矩阵更丰富的低维嵌入。两种模型在低秩嵌入中保持数据局部结构的能力已得到适当验证。低维嵌入相对于原始数据的优越性证明了降维的必要性。两种模型的优越性也通过分别与九种其他成熟的降维算法在五个流行数据集上的性能比较得到了验证。此外,还给出了模型的计算复杂度和收敛性分析,证明了模型的优越性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑