Large-scale data classification based on the integrated fusion of fuzzy learning and graph neural network

人工智能 计算机科学 机器学习 深度学习 模糊逻辑 人工神经网络 保险丝(电气) 神经模糊 图形 模糊控制系统 理论计算机科学 电气工程 工程类
作者
Václav Snåšel,Martin Štěpnička,Varun Ojha,Ponnuthurai Nagaratnam Suganthan,Ruobin Gao,Lingping Kong
出处
期刊:Information Fusion [Elsevier]
卷期号:102: 102067-102067 被引量:2
标识
DOI:10.1016/j.inffus.2023.102067
摘要

Deep learning and fuzzy models provide powerful and practical techniques for solving large-scale deep-learning tasks. The fusion technique on deep learning and fuzzy system are generally classified into ensemble and integrated modes and materializes in information fusion, model fusion, and feature fusion. In an ensemble-based fusion, the fuzzy model either acts as an activation function or is operated as a separate process aggregating/preprocessing the information. Some early attempts in the field have successfully fused deep neural networks and fuzzy modeling concepts in ensemble mode. However, no effective attempts were made to fuse fuzzy models as an integrated feature-level fusion learning with graph neural networks (GNNs). This is mainly due to two challenges related to this fusion: (1) the number of fuzzy rules grows exponentially with the number of features that causes computational inefficiency, and (2) the solution space created by this fusion of fuzzy rules becomes complex due to multiple regression relations between inputs and outputs. Additionally, a simple linear regression at the output space would not be sufficient to model deep learning tasks. Therefore, this paper addresses these challenges by proposing a feature-level fusion method to fuse deep learning and fuzzy modeling where the latter technique is for integrated feature learning, called fuzzy forest graph neural network (FuzzyGNN), which creates a fuzzy learning forest fusing the linear graph transformers for deep learning tasks. We conducted experiments on fourteen machine learning datasets to test and validate the efficiency of the proposed FuzzyGNN model. Compared to state-of-the-art methods, our algorithm achieves the best results on four out of five machine learning datasets. The source code will be available at https://github.com/lingping-fuzzy/ and https://github.com/P-N-Suganthan.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
huangyao完成签到 ,获得积分10
刚刚
SciGPT应助杜佳月采纳,获得10
1秒前
静修者z完成签到,获得积分10
2秒前
123发布了新的文献求助10
5秒前
友好的不言完成签到,获得积分10
5秒前
大方大树完成签到,获得积分20
8秒前
11秒前
云上人发布了新的文献求助10
12秒前
Luke Gee发布了新的文献求助10
12秒前
冬瓜发布了新的文献求助10
14秒前
15秒前
pentjy发布了新的文献求助10
17秒前
123完成签到,获得积分10
18秒前
林楠发布了新的文献求助10
19秒前
20秒前
21秒前
21秒前
sky发布了新的文献求助10
22秒前
wyzhou20完成签到,获得积分10
23秒前
YvonneChem发布了新的文献求助10
24秒前
24秒前
Orange应助jiang采纳,获得10
25秒前
25秒前
生动白莲完成签到,获得积分10
26秒前
Sg发布了新的文献求助10
26秒前
老实怀蝶应助Wlx采纳,获得10
27秒前
youyou发布了新的文献求助10
27秒前
28秒前
28秒前
顺利的若灵完成签到,获得积分10
28秒前
28秒前
CipherSage应助夜影阑珊采纳,获得10
29秒前
29秒前
星空完成签到,获得积分20
30秒前
李爱国应助wjq采纳,获得10
30秒前
远方完成签到,获得积分10
31秒前
小欣完成签到,获得积分10
32秒前
星空发布了新的文献求助10
33秒前
宣宣发布了新的文献求助20
33秒前
CodeCraft应助义气的德天采纳,获得10
33秒前
高分求助中
Earth System Geophysics 1000
Semiconductor Process Reliability in Practice 650
Studies on the inheritance of some characters in rice Oryza sativa L 600
Medicina di laboratorio. Logica e patologia clinica 600
《关于整治突出dupin问题的实施意见》(厅字〔2019〕52号) 500
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
Language injustice and social equity in EMI policies in China 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3207260
求助须知:如何正确求助?哪些是违规求助? 2856664
关于积分的说明 8106335
捐赠科研通 2521831
什么是DOI,文献DOI怎么找? 1355240
科研通“疑难数据库(出版商)”最低求助积分说明 642172
邀请新用户注册赠送积分活动 613472