FedNE:用于降维的代理辅助联合邻域嵌入

Ziwei Li, Xiaoqi Wang, Hong-You Chen, Han-Wei Shen, Wei-Lun Chao
{"title":"FedNE:用于降维的代理辅助联合邻域嵌入","authors":"Ziwei Li, Xiaoqi Wang, Hong-You Chen, Han-Wei Shen, Wei-Lun Chao","doi":"arxiv-2409.11509","DOIUrl":null,"url":null,"abstract":"Federated learning (FL) has rapidly evolved as a promising paradigm that\nenables collaborative model training across distributed participants without\nexchanging their local data. Despite its broad applications in fields such as\ncomputer vision, graph learning, and natural language processing, the\ndevelopment of a data projection model that can be effectively used to\nvisualize data in the context of FL is crucial yet remains heavily\nunder-explored. Neighbor embedding (NE) is an essential technique for\nvisualizing complex high-dimensional data, but collaboratively learning a joint\nNE model is difficult. The key challenge lies in the objective function, as\neffective visualization algorithms like NE require computing loss functions\namong pairs of data. In this paper, we introduce \\textsc{FedNE}, a novel\napproach that integrates the \\textsc{FedAvg} framework with the contrastive NE\ntechnique, without any requirements of shareable data. To address the lack of\ninter-client repulsion which is crucial for the alignment in the global\nembedding space, we develop a surrogate loss function that each client learns\nand shares with each other. Additionally, we propose a data-mixing strategy to\naugment the local data, aiming to relax the problems of invisible neighbors and\nfalse neighbors constructed by the local $k$NN graphs. We conduct comprehensive\nexperiments on both synthetic and real-world datasets. The results demonstrate\nthat our \\textsc{FedNE} can effectively preserve the neighborhood data\nstructures and enhance the alignment in the global embedding space compared to\nseveral baseline methods.","PeriodicalId":501301,"journal":{"name":"arXiv - CS - Machine Learning","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction\",\"authors\":\"Ziwei Li, Xiaoqi Wang, Hong-You Chen, Han-Wei Shen, Wei-Lun Chao\",\"doi\":\"arxiv-2409.11509\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Federated learning (FL) has rapidly evolved as a promising paradigm that\\nenables collaborative model training across distributed participants without\\nexchanging their local data. Despite its broad applications in fields such as\\ncomputer vision, graph learning, and natural language processing, the\\ndevelopment of a data projection model that can be effectively used to\\nvisualize data in the context of FL is crucial yet remains heavily\\nunder-explored. Neighbor embedding (NE) is an essential technique for\\nvisualizing complex high-dimensional data, but collaboratively learning a joint\\nNE model is difficult. The key challenge lies in the objective function, as\\neffective visualization algorithms like NE require computing loss functions\\namong pairs of data. In this paper, we introduce \\\\textsc{FedNE}, a novel\\napproach that integrates the \\\\textsc{FedAvg} framework with the contrastive NE\\ntechnique, without any requirements of shareable data. To address the lack of\\ninter-client repulsion which is crucial for the alignment in the global\\nembedding space, we develop a surrogate loss function that each client learns\\nand shares with each other. Additionally, we propose a data-mixing strategy to\\naugment the local data, aiming to relax the problems of invisible neighbors and\\nfalse neighbors constructed by the local $k$NN graphs. We conduct comprehensive\\nexperiments on both synthetic and real-world datasets. The results demonstrate\\nthat our \\\\textsc{FedNE} can effectively preserve the neighborhood data\\nstructures and enhance the alignment in the global embedding space compared to\\nseveral baseline methods.\",\"PeriodicalId\":501301,\"journal\":{\"name\":\"arXiv - CS - Machine Learning\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Machine Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11509\",\"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 - CS - Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11509","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

联盟学习(Federated Learning,FL)已迅速发展成为一种前景广阔的范式,它能让分布式参与者在不改变本地数据的情况下进行协作模型训练。尽管联合学习在计算机视觉、图学习和自然语言处理等领域有着广泛的应用,但在联合学习的背景下,开发一种能有效用于可视化数据的数据投影模型至关重要,但这一问题仍未得到充分探索。邻域嵌入(NE)是将复杂的高维数据可视化的重要技术,但协同学习联合 NE 模型却很困难。关键的挑战在于目标函数,因为有效的可视化算法(如 NE)需要计算数据对之间的损失函数。在本文中,我们介绍了一种新方法--textsc{FedNE},它将textsc{FedAvg}框架与对比NE技术整合在一起,而不需要任何可共享数据。为了解决缺乏客户端间排斥的问题(这对全局嵌入空间中的配准至关重要),我们开发了一种替代损失函数,每个客户端都可以学习并相互共享该函数。此外,我们还提出了一种数据混合策略来补充本地数据,旨在放宽本地 $k$NN 图构建的隐形邻居和假邻居问题。我们在合成数据集和真实世界数据集上进行了全面的实验。结果表明,与其他基线方法相比,我们的文本{FedNE}能有效地保留邻域数据结构,并增强全局嵌入空间的对齐度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction
Federated learning (FL) has rapidly evolved as a promising paradigm that enables collaborative model training across distributed participants without exchanging their local data. Despite its broad applications in fields such as computer vision, graph learning, and natural language processing, the development of a data projection model that can be effectively used to visualize data in the context of FL is crucial yet remains heavily under-explored. Neighbor embedding (NE) is an essential technique for visualizing complex high-dimensional data, but collaboratively learning a joint NE model is difficult. The key challenge lies in the objective function, as effective visualization algorithms like NE require computing loss functions among pairs of data. In this paper, we introduce \textsc{FedNE}, a novel approach that integrates the \textsc{FedAvg} framework with the contrastive NE technique, without any requirements of shareable data. To address the lack of inter-client repulsion which is crucial for the alignment in the global embedding space, we develop a surrogate loss function that each client learns and shares with each other. Additionally, we propose a data-mixing strategy to augment the local data, aiming to relax the problems of invisible neighbors and false neighbors constructed by the local $k$NN graphs. We conduct comprehensive experiments on both synthetic and real-world datasets. The results demonstrate that our \textsc{FedNE} can effectively preserve the neighborhood data structures and enhance the alignment in the global embedding space compared to several baseline methods.
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
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信