计算机科学 ›› 2026, Vol. 53 ›› Issue (4): 48-56.doi: 10.11896/jsjkx.251000068
云帆, 余志文, 杨楷翔
YUN Fan, YU Zhiwen, YANG Kaixiang
摘要： 在高维小样本分类任务中,宽度学习系统(Broad Learning System,BLS)因其高效的特性而备受关注。然而,原始的单层BLS的特征提取能力有限,难以处理复杂的高维数据。随机节点生成机制导致直接堆叠BLS隐层时出现节点冗余,模型性能难以提升。为解决上述问题,提出了一种集成堆叠BLS算法。所提算法利用前一层BLS的输出作为增强特征,将其与按分类置信度加权的原始特征进行拼接后输入下一层BLS,不断提高深层特征表达能力。通过元学习器池集成多个BLS层的输出,增强了原始单层BLS的高维特征提取能力,从而提升了模型的泛化性能。此外,考虑到高维数据复杂多变的特性,设计了动态集成框架,根据数据难度动态调整模型的复杂度。所提方法在保持模型性能的同时,进一步提升了集成效率。消融实验证明了所提算法的各个模块的有效性,对比实验证明了所提算法在高维疾病数据上的优越分类性能。
中图分类号:
| [1]CHEN C L P,LIU Z.Broad learning system:A new learning paradigm and system without going deep[C]//Proceedings of 32nd Youth Academicannual Conference of Chinese Association of Automation.IEEE,2017:1271-1276. [2]CHEN C L P,LIU Z.Broad learning system:An effective and efficient incremental learning system without the need for deep architecture[J].IEEE Transactions on Neural Networks and Learning Systems,2018,29(1):10-24. [3]YUN F,YU Z,YANG K,et al.Adaboost-stacking based on incremental broad learning system[J].IEEE Transactions on Knowledge and Data Engineering,2024,36:7585-7599. [4]PAO Y H,TAKEFUJI Y.Functional-link Net Computing:Theory,System Architecture,and Functionalities[J].Computer,1992,25:76-79. [5]YUN F,YU Z,YANG K,Broad Learning System in Data Mi-ning and Machine Lear-ning[J].Data Mining and Machine Learning,2025,1(1):100002. [6]ZHANG L,YU Z,YANG K,et al.Transferable and discriminative broad network for unsupervised domain adaptation[J].Knowledge-Based Systems,2025,315:113297. [7]HU X,CHEN C L P,ZHANG T.Broad metric learning:A fast and efficient discriminative metric learning model[J].IEEE Transactions on Cybernetics,2010,55(10):14. [8]YU Z,ZHONG Z,YANG K,et al.Broad learning autoencoder with graph structure for data clustering[J].IEEE Transactions on Knowledge and Data Engineering,2024,36(1):49-61. [9]CHEN W,YANG K,ZHANG W,et al.Double-kernelizedweighted broad learning system for imbalanced data[J].Neural Computing and Applications,2022,34(22):19923-19936. [10]CHEN W,YANG K,YU Z,et al.Double-kernel based class-specific broad learning system for multiclass imbalance learning[J].Knowledge-Based Systems,2022,253:109535. [11]YANG K,YU Z,CHEN C L P,et al.Incremental weighted ensemble broad learning system for imbalanced data[J].IEEE Transactions on Knowledge and Data Engineering,2021,34:5809-5824. [12]ZHANG T,LIU Z,WANG X,et al.Facial expression recognition via broad learning system[C]//Proceedings of IEEE International Conference on Systems,Man,and Cybernetics.IEEE,2018:1898-1902. [13]LEI C,GUO J,CHEN C L P.Convbls:An effective and efficient incremental convolutional broad learning system combining deep and broad representations[J].IEEE Transactions on Artificial Intelligence,2024,5(10):5075-5089. [14]YUN F,YU Z,YANG K,et al.Ensemble multi-kernel broadlearning system for disease diagnosis[C]//Proceedings of IEEE International Conference on Medical Artificial Intelligence.IEEE,2024:97-104. [15]LIN M,YANG K,YU Z,et al.Hybrid ensemble broad learning system for network intrusion detection[J].IEEE Transactions on Industrial Informatics,2024,20(4):5622-5633. [16]YANG K,SHI Y,YU Z,et al.Stacked one-class broad learning system for intrusion detection in industry 4.0[J].IEEE Transactions on Industrial Informatics,2023,19:251-260. [17]LIU Z,CHEN C L P,FENG S,et al.Stacked broad learning system:From incremental flatted structure to deep model[J].IEEE Transactions on Systems,Man,and Cybernetics:Systems,2020,51:209-222. [18]XIE R,WANG S.Downsizing and enhancing broad learning systems by feature augmentation and residuals boosting[J].Complex & Intelligent Systems,2020,6:411-429. [19]XIE R,VONG C,CHEN C L P,et al.Dynamic network structure:Doubly stacking broad learning systems with residuals and simpler linear model transmission[J].IEEE Transactions on Emerging Topics in Computational Intelligence,2022,6:1378-1395. [20]CHEN C L P,LIU Z,FENG S.Universal Approximation Capability of Broad Learning System and Its Structural Variations[J].IEEE Transactions on Neural Networks and Learning Systems,2019,30:1191-1204. [21]YI J,HUANG J,ZHOU W,et al.Intergroup cascade broadlearning system with optimized parameters for chaotic time series prediction[J].IEEE Transactions on Artificial Intelligence,2022,3:709-721. [22]DONG X,YU Z,CAO W,et al.A survey on ensemble learning[J].Frontiers of Computer Science,2020,14(2):241-258. [23]BREIMAN L.Bagging predictors[J].Machine Learning,1996,24(2):123-140. [24]HASTIE T,ROSSET S,ZHU J,et al.Multi-class adaboost[J].Statistics and its Interface,2009,2(3):349-360. [25]WOLPERT D.Stacked Generalization[J].Neural Networks,1992,5:241-259. [26]LI J,CHENG K,WANG S,et al.Feature Selection:A Data Perspective[J].ACM Computing Surveys,2016,50(6). [27]YAN Y,GUO W,WANG L.Broad learning system based on ensemble learning[C]//Proceedings of International Conference on Artificial Intelligence,Big Data and Algorithms.Chengdu:IEEE Press,2021:62-67. [28]WU C,QIU T,ZHANG C,et al.Ensemble strategy utilizing a broad learning system for indoor fingerprint localization[J].IEEE Internet of Things Journal,2021,9(4):3011-3022. [29]FAN X,ZHANG S.Lpi-bls:Predicting lncrna-protein interactions with a broad learning system-based stacked ensemble classifier[J].Neurocomputing,2019,370:88-93. [30]YU Z,LAN K,LIU Z,et al.Progressive ensemble kernel based broad learning system for noisy data classification[J].IEEE Transactions on Cybernetics,2022,52(9):9656-9669. [31]ZHAO B,YANG D,ZBSG H R.Filter-wrapper combined feature selection and adaboost-weighted broad learning system for transformer fault diagnosis under imbalanced samples[J].Neurocomputing,2023,560(1):1.1-1.12. [32]GAO Y,MIAO H,CHEN C L P,et al.Explosive cyber security threats during covid-19 pandemic and a novel tree-based broad learning system to overcome[J].IEEE Transactions on Intelligent Transportation Systems,2022,25(1):1-10. [33]COX D.The Regression Analysis of Binary Sequences[J].Journal of the Royal Statistical Society.Series B:Methodological,1958,20(2):215-242. [34]QUINLAN J.Induction of decision trees[J].Machine Learning,1986,1(1):81-106. [35]BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32. [36]ZHANG M,ZHOU Z.Ml-knn:A lazy learning approach tomulti-label learning[J].Pattern Recognition,2007,40(7):2038-2048. [37]HEARST M,DUMAIS S,OSUNA E,et al.Support vector machines[J].IEEE Intelligent Systems and their applications,1998,13(4):18-28. [38]ZHOU Z,FENG J.Deep forest:Towards an alternative to deep neural networks[C]//Proceedings of International Joint Confe-rence on Artificial Intelligence.Melbourne:Morgan Kaufmann,2017:3553-3559. [39]CHEN T,GUESTRIN C.Xgboost:A scalable tree boosting system[C]//Proceedings of ACM SIGKDD International Confe-rence on Knowledge Discovery and Data Mining.San Francisco:ACM,2016:785-794. [40]XU Y,YU Z,CAO W,et al.A Novel Classifier Ensemble Me-thod Based on Subspace Enhancement for High-Dimensional Data Classification[J].IEEE Transactions on Knowledge and Data Engineering,2023,35(1):16-30. |
| [1] | 邹晓阳, 鞠恒荣, 曹金鑫, 马星如, 黄嘉爽, 丁卫平. 图正则化模糊自动编码器的重叠社区检测 Overlapping Community Detection with Graph Regularized Fuzzy Autoencoder 计算机科学, 2026, 53(3): 207-213. https://doi.org/10.11896/jsjkx.250100093 |
| [2] | 付超, 余良菊, 常文军. 基于LLaMa3和Choquet积分的最优相似度选择集成学习方法 Selective Ensemble Learning Method for Optimal Similarity Based on LLaMa3 and Choquet Integrals 计算机科学, 2025, 52(9): 80-87. https://doi.org/10.11896/jsjkx.250100150 |
| [3] | 刘思行, 许硕洋, 徐鹤, 季一木. 基于机器学习的介入式葡萄糖传感器故障监测模型 Machine Learning Based Interventional Glucose Sensor Fault Monitoring Model 计算机科学, 2025, 52(9): 106-118. https://doi.org/10.11896/jsjkx.250300037 |
| [4] | 包晟宏, 姚有健, 李小丫, 陈文. 集成式PU学习方法PUEVD及其在软件源码漏洞检测中的应用 Integrated PU Learning Method PUEVD and Its Application in Software Source CodeVulnerability Detection 计算机科学, 2025, 52(6A): 241100144-9. https://doi.org/10.11896/jsjkx.241100144 |
| [5] | 成凯, 汤卫东, 谈林涛, 陈佳, 李鑫. 基于归一化处理和TrafficLLM的网络攻击缓解框架 Network Attack Mitigation Framework Based on Normalized Processing and TrafficLLM 计算机科学, 2025, 52(6A): 250200080-9. https://doi.org/10.11896/jsjkx.250200080 |
| [6] | 王瑞, 汤占军. 基于多特征融合与集成学习的风机叶片缺陷检测方法 Multi-feature Fusion and Ensemble Learning-based Wind Turbine Blade Defect Detection Method 计算机科学, 2025, 52(6A): 240900138-8. https://doi.org/10.11896/jsjkx.240900138 |
| [7] | 刘成明, 李海霞, 李韶川, 李英豪. 基于多尺度数据的股票操纵检测集成模型 Ensemble Learning Model for Stock Manipulation Detection Based on Multi-scale Data 计算机科学, 2025, 52(6A): 240700108-8. https://doi.org/10.11896/jsjkx.240700108 |
| [8] | 何元康, 马海龙, 胡涛, 江逸茗. 基于特征差分选择的集成模型流量对抗样本防御架构 Defense Architecture for Adversarial Examples of Ensemble Model Traffic Based on FeatureDifference Selection 计算机科学, 2025, 52(4): 369-380. https://doi.org/10.11896/jsjkx.240200092 |
| [9] | 陈维国, 张高峰, 贾晟, 徐本柱, 郑利平. 基于MOBSF_rule的安卓恶意软件检测方法 MOBSF_rule Based Android Malware Detection Method 计算机科学, 2025, 52(11A): 250200120-11. https://doi.org/10.11896/jsjkx.250200120 |
| [10] | 郭嘉铭, 杜文韬, 杨超. 一种基于深度分区聚合的神经网络后门样本过滤方法 Neural Network Backdoor Sample Filtering Method Based on Deep Partition Aggregation 计算机科学, 2025, 52(11): 425-433. https://doi.org/10.11896/jsjkx.240900007 |
| [11] | 韩威, 姜淑娟, 周伟. 基于CodeBERT和Stacking集成学习的补丁正确性验证方法 Patch Correctness Verification Method Based on CodeBERT and Stacking Ensemble Learning 计算机科学, 2025, 52(1): 250-258. https://doi.org/10.11896/jsjkx.240100019 |
| [12] | 卢徐霖, 李志华. 融合多模态物联网设备指纹与集成学习的物联网设备识别方法 IoT Device Recognition Method Combining Multimodal IoT Device Fingerprint and Ensemble Learning 计算机科学, 2024, 51(9): 371-382. https://doi.org/10.11896/jsjkx.230800076 |
| [13] | 王屹阳, 刘发贵, 彭玲霞, 钟国祥. 融合AP聚类算法和宽度学习系统的分布外硬盘故障预测 Out-of-Distribution Hard Disk Failure Prediction with Affinity Propagation Clustering and Broad Learning Systems 计算机科学, 2024, 51(8): 63-74. https://doi.org/10.11896/jsjkx.230600103 |
| [14] | 卓佩妍, 张瑶娜, 刘炜, 刘自金, 宋友. CTGANBoost:基于CTGAN与Boosting的信贷欺诈检测研究 CTGANBoost:Credit Fraud Detection Based on CTGAN and Boosting 计算机科学, 2024, 51(6A): 230600199-7. https://doi.org/10.11896/jsjkx.230600199 |
| [15] | 梁美彦, 范莹莹, 王琳. 基于多距离测度异质集成学习的结肠病理图像细粒度分类研究 Fine-grained Colon Pathology Images Classification Based on Heterogeneous Ensemble Learningwith Multi-distance Measures 计算机科学, 2024, 51(6A): 230400043-7. https://doi.org/10.11896/jsjkx.230400043 |
|
||
首页