MIML library: A modular and flexible library for multi-instance multi-label learning

被引：2
作者：
Belmonte, Alvaro [1 ]
Zafra, Amelia [1 ,2 ]
Gibaja, Eva [1 ,2 ,3 ]
机构：
[1] Univ Cordoba, Dept Comp Sci & Numer Anal, Cordoba, Spain
[2] Univ Cordoba, Andalusian Res Inst Data Sci & Computat Intelligen, Cordoba, Spain
[3] Univ Cordoba, Dept Comp Sci & Numer Anal, Campus Rabanales,Albert Einstein Bldg, 3rd floor, Cordoba 14071, Spain
来源：
NEUROCOMPUTING | 2022年 / 500卷
关键词：
Multi-instance learning; Multi-label learning; Weka; Mulan; Classification; CLASSIFICATION;
D O I：
10.1016/j.neucom.2022.05.068
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
MIML library is a Java software tool to develop, test, and compare classification algorithms for multiinstance multi-label (MIML) learning. The library includes 43 algorithms and provides a specific format and facilities for data managing and partitioning, holdout and cross-validation methods, standard metrics for performance evaluation, and generation of reports. In addition, algorithms can be executed through xml configuration files without needing to program. It is platform-independent, extensible, free, opensource, and available on GitHub under the GNU General Public License.(c) 2022 Elsevier B.V. All rights reserved.
引用
收藏
页码：632 / 636
页数：5
相关论文
共 40 条
  • [1] Andrews Stuart, 2002, Advances in Neural Information Processing Systems, P561
  • [2] [Anonymous], 2009, ACM SIGKDD Explorations Newsletter, DOI DOI 10.1145/1656274.1656278
  • [3] [Anonymous], 2008, PROC ECML PKDD 2008
  • [4] [Anonymous], 2005, PROC ICM, DOI DOI 10.1145/1102351.1102439
  • [5] [Anonymous], 2005, Proceedings of the 22nd International Conference on Machine Learning, ICML'05, page
  • [6] [Anonymous], 2002, ICML
  • [7] [Anonymous], 2013, P 23 INT JOINT C ART
  • [8] [Anonymous], 2007, Advances in Neural Info. Process. Syst.
  • [9] Auer P, 2004, LECT NOTES COMPUT SC, V3201, P63
  • [10] Bjerring L, 2011, LECT NOTES ARTIF INT, V7106, P41, DOI 10.1007/978-3-642-25832-9_5
1234