CNN2GNN:如何将CNN与GNN连接起来。

Ziheng Jiao, Hongyuan Zhang, Xuelong Li
{"title":"CNN2GNN:如何将CNN与GNN连接起来。","authors":"Ziheng Jiao, Hongyuan Zhang, Xuelong Li","doi":"10.1109/TPAMI.2025.3583357","DOIUrl":null,"url":null,"abstract":"<p><p>Thanks to extracting the intra-sample representation, the convolution neural network (CNN) has achieved excellent performance in vision tasks. However, its numerous convolutional layers take a higher training expense. Recently, graph neural networks (GNN), a bilinear model, have succeeded in exploring the underlying topological relationship among the graph data with a few graph neural layers. Unfortunately, due to the lack of graph structure and high-cost inference on large-scale scenarios, it cannot be directly utilized on non-graph data. Inspired by these complementary strengths and weaknesses, we discuss a natural question, how to bridge these two heterogeneous networks? In this paper, we propose a novel CNN2GNN framework to unify CNN and GNN together via distillation. Firstly, to break the limitations of GNN, we design a differentiable sparse graph learning module as the head of the networks. It can dynamically learn the graph for inductive learning. Then, a response-based distillation is introduced to transfer the knowledge and bridge these two heterogeneous networks. Notably, due to extracting the intra-sample representation of a single instance and the topological relationship among the datasets simultaneously, the performance of the distilled \"boosted\" two-layer GNN on Mini-ImageNet is much higher than CNN containing dozens of layers, such as ResNet152.</p>","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":"PP ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CNN2GNN: How to Bridge CNN with GNN.\",\"authors\":\"Ziheng Jiao, Hongyuan Zhang, Xuelong Li\",\"doi\":\"10.1109/TPAMI.2025.3583357\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Thanks to extracting the intra-sample representation, the convolution neural network (CNN) has achieved excellent performance in vision tasks. However, its numerous convolutional layers take a higher training expense. Recently, graph neural networks (GNN), a bilinear model, have succeeded in exploring the underlying topological relationship among the graph data with a few graph neural layers. Unfortunately, due to the lack of graph structure and high-cost inference on large-scale scenarios, it cannot be directly utilized on non-graph data. Inspired by these complementary strengths and weaknesses, we discuss a natural question, how to bridge these two heterogeneous networks? In this paper, we propose a novel CNN2GNN framework to unify CNN and GNN together via distillation. Firstly, to break the limitations of GNN, we design a differentiable sparse graph learning module as the head of the networks. It can dynamically learn the graph for inductive learning. Then, a response-based distillation is introduced to transfer the knowledge and bridge these two heterogeneous networks. Notably, due to extracting the intra-sample representation of a single instance and the topological relationship among the datasets simultaneously, the performance of the distilled \\\"boosted\\\" two-layer GNN on Mini-ImageNet is much higher than CNN containing dozens of layers, such as ResNet152.</p>\",\"PeriodicalId\":94034,\"journal\":{\"name\":\"IEEE transactions on pattern analysis and machine intelligence\",\"volume\":\"PP \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-07-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on pattern analysis and machine intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TPAMI.2025.3583357\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on pattern analysis and machine intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TPAMI.2025.3583357","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

卷积神经网络(CNN)通过提取样本内表示,在视觉任务中取得了优异的性能。然而,其众多的卷积层需要较高的训练费用。近年来,图神经网络(GNN)作为一种双线性模型,成功地利用少量的图神经层来探索图数据之间的底层拓扑关系。遗憾的是,由于缺乏图结构和大规模场景下的高成本推理,它不能直接用于非图数据。受这些互补的优势和劣势的启发,我们讨论了一个自然的问题,如何弥合这两个异构的网络?在本文中,我们提出了一个新的CNN2GNN框架,通过蒸馏将CNN和GNN统一在一起。首先,为了突破GNN的局限性,我们设计了一个可微稀疏图学习模块作为网络的头部。它可以动态学习图,进行归纳学习。然后,引入基于响应的精馏来传递知识,并在这两个异构网络之间架起桥梁。值得注意的是,由于同时提取单个实例的样本内表示和数据集之间的拓扑关系,因此在Mini-ImageNet上提取的“增强”两层GNN的性能远远高于包含数十层的CNN,如ResNet152。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
CNN2GNN: How to Bridge CNN with GNN.

Thanks to extracting the intra-sample representation, the convolution neural network (CNN) has achieved excellent performance in vision tasks. However, its numerous convolutional layers take a higher training expense. Recently, graph neural networks (GNN), a bilinear model, have succeeded in exploring the underlying topological relationship among the graph data with a few graph neural layers. Unfortunately, due to the lack of graph structure and high-cost inference on large-scale scenarios, it cannot be directly utilized on non-graph data. Inspired by these complementary strengths and weaknesses, we discuss a natural question, how to bridge these two heterogeneous networks? In this paper, we propose a novel CNN2GNN framework to unify CNN and GNN together via distillation. Firstly, to break the limitations of GNN, we design a differentiable sparse graph learning module as the head of the networks. It can dynamically learn the graph for inductive learning. Then, a response-based distillation is introduced to transfer the knowledge and bridge these two heterogeneous networks. Notably, due to extracting the intra-sample representation of a single instance and the topological relationship among the datasets simultaneously, the performance of the distilled "boosted" two-layer GNN on Mini-ImageNet is much higher than CNN containing dozens of layers, such as ResNet152.

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:604180095
Book学术官方微信