[1]LIU Zhiqiang,TAN Haoyu,HAN Aokun,et al.Multi-label imbalanced data oversampling based on natural neighborhood and data gravity[J].CAAI Transactions on Intelligent Systems,2026,21(3):651-665.[doi:10.11992/tis.202505019]
Copy

Multi-label imbalanced data oversampling based on natural neighborhood and data gravity

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 3 Page number: 651-665 Column: 学术论文—机器学习 Public date: 2026-05-05
Title:
Multi-label imbalanced data oversampling based on natural neighborhood and data gravity
Author(s):
LIU Zhiqiang;  TAN Haoyu;  HAN Aokun;  WANG Weiqing;  YAN Yuanting;  ZHANG Yanping
College of Computer Science and Technology, Anhui University, Hefei 230601, China
Keywords:
multi-label; imbalanced learning; oversampling; natural neighborhood; data gravitation; label assignment; class overlap; classification
CLC:
TP311
DOI:
10.11992/tis.202505019
Abstract:
In multi-label imbalanced data classification, oversampling has emerged as a mainstream technique. However, how to design effective sampling strategies that capture the local distribution information of samples while avoiding the introduction of overlapping samples during the synthesis process, and reducing the inter-class separability, remains a key challenge for oversampling methods. To this end, we propose a novel multi-label oversampling method based on natural neighborhood and data gravitation. Firstly, the method constructs adaptive natural neighborhood structures in feature space to capture local distribution information. Then, it employs label similarity to guide auxiliary sample selection, assigning higher weights to relatively safe auxiliary samples to mitigate class overlapping risk. Finally, it constructs a dynamic label assignment mechanism with the data gravitation model to generate label information, and avoiding the possible inter-class conflicts inherent in fixed label allocation rules. Experimental resultson 14 imbalanced datasets demonstrate that the proposed algorithm outperforms state-of-the-art methods in three performance metrics.
References:
[1] YAN Yuanting, ZHENG Zhong, ZHANG Yiwen, et al. CPS-3WS: a critical pattern supported three-way sampling method for classifying class-overlapped imbalanced data[J]. Information sciences, 2024, 676: 120835
[2] 严远亭, 马迎澳, 任艳平, 等. 基于构造性神经网络与全局密度信息的不平衡数据欠采样方法[J]. 计算机科学, 2023, 50(10): 48-58 YAN Yuanting, MA Ying’ao, REN Yanping, et al. Imbalanced undersampling based on constructive neural network and global density information[J]. Computer science, 2023, 50(10): 48-58
[3] 范洪旗, 严远亭, 张以文, 等. 学习困难与泛化能力感知的软件缺陷预测过采样方法[J]. 计算机集成制造系统, 2024, 30(8): 2663-2671 FAN Hongqi, YAN Yuanting, ZHANG Yiwen, et al. Software defect prediction oversampling technique with generalization and difficulty-aware[J]. Computer integrated manufacturing systems, 2024, 30(8): 2663-2671
[4] 徐贞顺, 郑顺国, 苏梦瑶, 等. 基于双自适应约束的对抗学习过采样方法[J/OL]. 计算机科学, 1-16[2026-02-10]. https://link.cnki.net/urlid/50.1075.tp.20251219.1013.002. XU Zhenshun, ZHENG Shunguo, SU Mengyao, et al. Adversarial learning with dual adaptive constraints for oversampling method[J/OL]. Computer Science, 1-16[2026-02-10]. https://link.cnki.net/urlid/50.1075.tp.20251219.1013.002.
[5] YAN Yuanting, ZHU Yuanwei, LIU Ruiqing, et al. Spatial distribution-based imbalanced undersampling[J]. IEEE transactions on knowledge and data engineering, 2023, 35(6): 6376-6391
[6] LILOGLOU T, MALONEY P, XINARIANOS G, et al. Sensitivity and limitations of high throughput fluorescent microsatellite analysis for the detection of allelic imbalance: application in lung tumors[J]. International journal of oncology, 2000, 16(1): 5-19
[7] JIANG Ting, WANG Deqing, SUN Leilei, et al. LightXML: transformer with dynamic negative sampling for high-performance extreme multi-label text classification[J]. Proceedings of the AAAI conference on artificial intelligence, 2021, 35(9): 7987-7994
[8] HE Zengxiang, CHU Pengpeng, LI Chenxi, et al. Compound fault diagnosis for photovoltaic arrays based on multi-label learning considering multiple faults coupling[J]. Energy conversion and management, 2023, 279: 116742
[9] HAN Meng, WU Hongxin, CHEN Zhiqiang, et al. A survey of multi-label classification based on supervised and semi-supervised learning[J]. International journal of machine learning and cybernetics, 2023, 14(3): 697-724
[10] AHMADI Z, KRAMER S. A label compression method for online multi-label classification[J]. Pattern recognition letters, 2018, 111: 64-71
[11] TSOUMAKAS G, KATAKIS I. Multi-label classification: an overview[J]. International journal of data warehousing and mining (IJDWM), 2007, 3(3): 1-13
[12] KOZIARSKI M. Potential Anchoring for imbalanced data classification[J]. Pattern recognition, 2021, 120: 108114
[13] CHARTE F, RIVERA A J, DEL JESUS M J, et al. Addressing imbalance in multilabel classification: measures and random resampling algorithms[J]. Neurocomputing, 2015, 163: 3-16
[14] ZHANG Minling, LI Yukun, YANG Hao, et al. Towards class-imbalance aware multi-label learning[J]. IEEE transactions on cybernetics, 2022, 52(6): 4459-4471
[15] ZHANG Minling, ZHOU Zhihua. A review on multi-label learning algorithms[J]. IEEE transactions on knowledge and data engineering, 2014, 26(8): 1819-1837
[16] NARESHPALSINGH J M, MODI H N. Multi-label classification methods: a comparative study[J]. International research journal of engineering and technology, 2017, 4(12): 263-270
[17] S?EZ J A, KRAWCZYK B, WO?NIAK M. Analyzing the oversampling of different classes and types of examples in multi-class imbalanced datasets[J]. Pattern recognition, 2016, 57: 164-178
[18] LIU Bin, BLEKAS K, TSOUMAKAS G. Multi-label sampling based on local label imbalance[J]. Pattern recognition, 2022, 122: 108294
[19] ZHANG Kai, MAO Zhaoyang, CAO Peng, et al. Label correlation guided borderline oversampling for imbalanced multi-label data learning[J]. Knowledge-based systems, 2023, 279: 110938
[20] ZHU Qingsheng, FENG Ji, HUANG Jinlong. Natural neighbor: a self-adaptive neighborhood method without parameter K[J]. Pattern recognition letters, 2016, 80: 30-36
[21] 冯骥, 张程, 朱庆生. 一种具有动态邻域特点的自适应最近邻居算法[J]. 计算机科学, 2017, 44(12): 194-201 FENG Ji, ZHANG Cheng, ZHU Qingsheng. Adaptive nearest neighbor algorithm with dynamic neighborhood[J]. Computer science, 2017, 44(12): 194-201
[22] CHARTE F, RIVERA A J, DEL JESUS M J, et al. MLSMOTE: approaching imbalanced multilabel learning through synthetic instance generation[J]. Knowledge-based systems, 2015, 89: 385-397
[23] ARYUNI M, FATICHAH C, YUNIARTI A. Resampling methods for imbalanced datasets in multi-label classification: a review[C]//2024 IEEE 14th Symposium on Computer Applications & Industrial Electronics. Penang: IEEE, 2024: 472-477.
[24] TSOUMAKAS G, VLAHAVAS I. Random k-labelsets: an ensemble method for multilabel classification[C]//Machine Learning: ECML 2007. Berlin: Springer, 2007: 406-417.
[25] PEREIRA R M, COSTA Y M G, SILLA C N Jr. MLTL: a multi-label approach for the Tomek Link undersampling algorithm[J]. Neurocomputing, 2020, 383: 95-105
[26] BATISTA G E A P A, PRATI R C, MONARD M C. A study of the behavior of several methods for balancing machine learning training data[J]. ACM SIGKDD explorations newsletter, 2004, 6(1): 20-29
[27] CHARTE F, RIVERA A J, DEL JESUS M J, et al. MLeNN: a first approach to heuristic multilabel undersampling[C]//Intelligent Data Engineering and Automated Learning. Cham: Springer, 2014: 1-9.
[28] LIU Bin, ZHOU Ao, WEI Bingkun, et al. Oversampling multi-label data based on natural neighbor and label correlation[J]. Expert systems with applications, 2025, 259: 125257
[29] CHARTE F, RIVERA A J, DEL JESUS M J, et al. Dealing with difficult minority labels in imbalanced mutilabel data sets[J]. Neurocomputing, 2019, 326: 39-53
[30] CHARTE F, RIVERA A J, DEL JESUS M J, et al. REMEDIAL-HwR: Tackling multilabel imbalance through label decoupling and data resampling hybridization[J]. Neurocomputing, 2019, 326: 110-122
[31] 许茂龙, 姜高霞, 王文剑. 基于异常检测的标签噪声过滤框架[J]. 计算机科学, 2024, 51(2): 87-99 XU Maolong, JIANG Gaoxia, WANG Wenjian. Label noise filtering framework based on outlier detection[J]. Computer science, 2024, 51(2): 87-99
[32] WANG Zhe, LI Yanqiong, LI Dongdong, et al. Entropy and gravitation based dynamic radius nearest neighbor classification for imbalanced problem[J]. Knowledge-based systems, 2020, 193: 105474
[33] BRINKER K, F?RNKRANZ J, H?LLERMEIER E. A unified model for multilabel classification and ranking[C]//17th European Conference on Artificial Intelligence. Riva del Garda: IOS Press, 2006: 489-493.
[34] READ J, PFAHRINGER B, HOLMES G, et al. Classifier chains for multi-label classification[J]. Machine learning, 2011, 85(3): 333-359
[35] ZHANG Minling, ZHOU Zhihua. ML-KNN: a lazy learning approach to multi-label learning[J]. Pattern recognition, 2007, 40(7): 2038-2048
[36] F?RNKRANZ J, H?LLERMEIER E, LOZA MENC?A E, et al. Multilabel classification via calibrated label ranking[J]. Machine learning, 2008, 73(2): 133-153
[37] SECHIDIS K, TSOUMAKAS G, VLAHAVAS I. On the stratification of multi-label data[C]//Machine Learning and Knowledge Discovery in Databases. Berlin: Springer, 2011: 145-158.
[38] REN Weishuo, ZHENG Yifeng, ZHANG Wenjie, et al. A novel ensemble over-sampling approach based Chebyshev inequality for imbalanced multi-label data[J]. Neurocomputing, 2025, 612: 128717
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems