Hyperbolic Binary Neural Network.

IF 10.2 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE IEEE transactions on neural networks and learning systems Pub Date : 2024-10-31 DOI:10.1109/TNNLS.2024.3485115
Jun Chen, Jingyang Xiang, Tianxin Huang, Xiangrui Zhao, Yong Liu
{"title":"Hyperbolic Binary Neural Network.","authors":"Jun Chen, Jingyang Xiang, Tianxin Huang, Xiangrui Zhao, Yong Liu","doi":"10.1109/TNNLS.2024.3485115","DOIUrl":null,"url":null,"abstract":"<p><p>Binary neural network (BNN) converts full-precision weights and activations into their extreme 1-bit counterparts, making it particularly suitable for deployment on lightweight mobile devices. While BNNs are typically formulated as a constrained optimization problem and optimized in the binarized space, general neural networks are formulated as an unconstrained optimization problem and optimized in the continuous space. This article introduces the hyperbolic BNN (HBNN) by leveraging the framework of hyperbolic geometry to optimize the constrained problem. Specifically, we transform the constrained problem in hyperbolic space into an unconstrained one in Euclidean space using the Riemannian exponential map. On the other hand, we also propose the exponential parametrization cluster (EPC) method, which, compared with the Riemannian exponential map, shrinks the segment domain based on a diffeomorphism. This approach increases the probability of weight flips, thereby maximizing the information gain in BNNs. Experimental results on CIFAR10, CIFAR100, and ImageNet classification datasets with VGGsmall, ResNet18, and ResNet34 models illustrate the superior performance of our HBNN over state-of-the-art methods.</p>","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":null,"pages":null},"PeriodicalIF":10.2000,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on neural networks and learning systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/TNNLS.2024.3485115","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Binary neural network (BNN) converts full-precision weights and activations into their extreme 1-bit counterparts, making it particularly suitable for deployment on lightweight mobile devices. While BNNs are typically formulated as a constrained optimization problem and optimized in the binarized space, general neural networks are formulated as an unconstrained optimization problem and optimized in the continuous space. This article introduces the hyperbolic BNN (HBNN) by leveraging the framework of hyperbolic geometry to optimize the constrained problem. Specifically, we transform the constrained problem in hyperbolic space into an unconstrained one in Euclidean space using the Riemannian exponential map. On the other hand, we also propose the exponential parametrization cluster (EPC) method, which, compared with the Riemannian exponential map, shrinks the segment domain based on a diffeomorphism. This approach increases the probability of weight flips, thereby maximizing the information gain in BNNs. Experimental results on CIFAR10, CIFAR100, and ImageNet classification datasets with VGGsmall, ResNet18, and ResNet34 models illustrate the superior performance of our HBNN over state-of-the-art methods.

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
双曲二元神经网络
二进制神经网络(BNN)将全精度权值和激活度转换为极端的 1 位对应值,因此特别适合部署在轻量级移动设备上。二值神经网络通常被表述为一个受限优化问题,并在二值化空间中进行优化,而一般神经网络则被表述为一个无约束优化问题,并在连续空间中进行优化。本文通过利用双曲几何框架来优化受限问题,介绍了双曲 BNN(HBNN)。具体来说,我们利用黎曼指数图将双曲空间中的有约束问题转化为欧几里得空间中的无约束问题。另一方面,我们还提出了指数参数化簇(EPC)方法,与黎曼指数图相比,该方法基于差分变形缩小了线段域。这种方法提高了权重翻转的概率,从而使 BNN 的信息增益最大化。使用 VGGsmall、ResNet18 和 ResNet34 模型在 CIFAR10、CIFAR100 和 ImageNet 分类数据集上的实验结果表明,我们的 HBNN 性能优于最先进的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
IEEE transactions on neural networks and learning systems
IEEE transactions on neural networks and learning systems COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-COMPUTER SCIENCE, HARDWARE & ARCHITECTURE
CiteScore
23.80
自引率
9.60%
发文量
2102
审稿时长
3-8 weeks
期刊介绍: The focus of IEEE Transactions on Neural Networks and Learning Systems is to present scholarly articles discussing the theory, design, and applications of neural networks as well as other learning systems. The journal primarily highlights technical and scientific research in this domain.
期刊最新文献
One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration. Hyperbolic Binary Neural Network. MAEMOT: Pretrained MAE-Based Antiocclusion 3-D Multiobject Tracking for Autonomous Driving. Spike-and-Slab Shrinkage Priors for Structurally Sparse Bayesian Neural Networks. Multi-Task Multi-Agent Reinforcement Learning With Interaction and Task Representations.
×
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