基于对称性结构矩阵的高效近似等价网络

Ashwin Samudre, Mircea Petrache, Brian D. Nord, Shubhendu Trivedi
{"title":"基于对称性结构矩阵的高效近似等价网络","authors":"Ashwin Samudre, Mircea Petrache, Brian D. Nord, Shubhendu Trivedi","doi":"arxiv-2409.11772","DOIUrl":null,"url":null,"abstract":"There has been much recent interest in designing symmetry-aware neural\nnetworks (NNs) exhibiting relaxed equivariance. Such NNs aim to interpolate\nbetween being exactly equivariant and being fully flexible, affording\nconsistent performance benefits. In a separate line of work, certain structured\nparameter matrices -- those with displacement structure, characterized by low\ndisplacement rank (LDR) -- have been used to design small-footprint NNs.\nDisplacement structure enables fast function and gradient evaluation, but\npermits accurate approximations via compression primarily to classical\nconvolutional neural networks (CNNs). In this work, we propose a general\nframework -- based on a novel construction of symmetry-based structured\nmatrices -- to build approximately equivariant NNs with significantly reduced\nparameter counts. Our framework integrates the two aforementioned lines of work\nvia the use of so-called Group Matrices (GMs), a forgotten precursor to the\nmodern notion of regular representations of finite groups. GMs allow the design\nof structured matrices -- resembling LDR matrices -- which generalize the\nlinear operations of a classical CNN from cyclic groups to general finite\ngroups and their homogeneous spaces. We show that GMs can be employed to extend\nall the elementary operations of CNNs to general discrete groups. Further, the\ntheory of structured matrices based on GMs provides a generalization of LDR\ntheory focussed on matrices with cyclic structure, providing a tool for\nimplementing approximate equivariance for discrete groups. We test GM-based\narchitectures on a variety of tasks in the presence of relaxed symmetry. We\nreport that our framework consistently performs competitively compared to\napproximately equivariant NNs, and other structured matrix-based compression\nframeworks, sometimes with a one or two orders of magnitude lower parameter\ncount.","PeriodicalId":501340,"journal":{"name":"arXiv - STAT - Machine Learning","volume":"6 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks\",\"authors\":\"Ashwin Samudre, Mircea Petrache, Brian D. Nord, Shubhendu Trivedi\",\"doi\":\"arxiv-2409.11772\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"There has been much recent interest in designing symmetry-aware neural\\nnetworks (NNs) exhibiting relaxed equivariance. Such NNs aim to interpolate\\nbetween being exactly equivariant and being fully flexible, affording\\nconsistent performance benefits. In a separate line of work, certain structured\\nparameter matrices -- those with displacement structure, characterized by low\\ndisplacement rank (LDR) -- have been used to design small-footprint NNs.\\nDisplacement structure enables fast function and gradient evaluation, but\\npermits accurate approximations via compression primarily to classical\\nconvolutional neural networks (CNNs). In this work, we propose a general\\nframework -- based on a novel construction of symmetry-based structured\\nmatrices -- to build approximately equivariant NNs with significantly reduced\\nparameter counts. Our framework integrates the two aforementioned lines of work\\nvia the use of so-called Group Matrices (GMs), a forgotten precursor to the\\nmodern notion of regular representations of finite groups. GMs allow the design\\nof structured matrices -- resembling LDR matrices -- which generalize the\\nlinear operations of a classical CNN from cyclic groups to general finite\\ngroups and their homogeneous spaces. We show that GMs can be employed to extend\\nall the elementary operations of CNNs to general discrete groups. Further, the\\ntheory of structured matrices based on GMs provides a generalization of LDR\\ntheory focussed on matrices with cyclic structure, providing a tool for\\nimplementing approximate equivariance for discrete groups. We test GM-based\\narchitectures on a variety of tasks in the presence of relaxed symmetry. We\\nreport that our framework consistently performs competitively compared to\\napproximately equivariant NNs, and other structured matrix-based compression\\nframeworks, sometimes with a one or two orders of magnitude lower parameter\\ncount.\",\"PeriodicalId\":501340,\"journal\":{\"name\":\"arXiv - STAT - Machine Learning\",\"volume\":\"6 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - STAT - Machine Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11772\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - STAT - Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11772","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

最近,人们对设计对称感知神经网络(NN)表现出宽松的等差性兴趣浓厚。这类神经网络的目标是在精确等差性和完全灵活性之间进行穿插,从而带来一致的性能优势。在另一项研究中,某些结构化参数矩阵--具有位移结构、以低位移秩(LDR)为特征的矩阵--已被用于设计小尺寸 NN。位移结构可实现快速函数和梯度评估,但主要通过压缩实现精确逼近经典卷积神经网络(CNN)。在这项工作中,我们提出了一个通用框架--基于对称结构矩阵的新颖构造--来构建近似等变的 NN,并显著减少参数数量。我们的框架通过使用所谓的群矩阵(GMs)整合了上述两方面的工作,GMs 是有限群正则表达式这一现代概念被遗忘的前身。GMs允许设计结构化矩阵--类似于LDR矩阵--将经典CNN的线性运算从循环群推广到一般有限群及其同质空间。我们证明,可以利用 GM 将 CNN 的所有基本操作扩展到一般离散群。此外,基于 GM 的结构矩阵理论提供了对 LDR 理论的概括,该理论侧重于具有循环结构的矩阵,为离散群提供了实现近似等差数列的工具。我们在各种任务中测试了在松弛对称性条件下基于 GM 的架构。结果表明,与近似等差数列网络和其他基于结构矩阵的压缩框架相比,我们的框架在性能上始终具有竞争力,有时甚至比它们低一到两个数量级的参数。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks
There has been much recent interest in designing symmetry-aware neural networks (NNs) exhibiting relaxed equivariance. Such NNs aim to interpolate between being exactly equivariant and being fully flexible, affording consistent performance benefits. In a separate line of work, certain structured parameter matrices -- those with displacement structure, characterized by low displacement rank (LDR) -- have been used to design small-footprint NNs. Displacement structure enables fast function and gradient evaluation, but permits accurate approximations via compression primarily to classical convolutional neural networks (CNNs). In this work, we propose a general framework -- based on a novel construction of symmetry-based structured matrices -- to build approximately equivariant NNs with significantly reduced parameter counts. Our framework integrates the two aforementioned lines of work via the use of so-called Group Matrices (GMs), a forgotten precursor to the modern notion of regular representations of finite groups. GMs allow the design of structured matrices -- resembling LDR matrices -- which generalize the linear operations of a classical CNN from cyclic groups to general finite groups and their homogeneous spaces. We show that GMs can be employed to extend all the elementary operations of CNNs to general discrete groups. Further, the theory of structured matrices based on GMs provides a generalization of LDR theory focussed on matrices with cyclic structure, providing a tool for implementing approximate equivariance for discrete groups. We test GM-based architectures on a variety of tasks in the presence of relaxed symmetry. We report that our framework consistently performs competitively compared to approximately equivariant NNs, and other structured matrix-based compression frameworks, sometimes with a one or two orders of magnitude lower parameter count.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Fitting Multilevel Factor Models Cartan moving frames and the data manifolds Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks Recurrent Interpolants for Probabilistic Time Series Prediction PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1