Guided Self-Training based Semi-Supervised Learning for Fraud Detection

被引:3
|
作者
Kumar, Awanish [1 ]
Ghosh, Soumyadeep [1 ]
Verma, Janu [1 ]
机构
[1] Mastercard, AI Garage, Gurgaon, India
来源
3RD ACM INTERNATIONAL CONFERENCE ON AI IN FINANCE, ICAIF 2022 | 2022年
关键词
adversarial attack; vulnerability detection; vulnerability mitigation; transaction level vulnerability; black box vulnerability detection;
D O I
10.1145/3533271.3561783
中图分类号
F8 [财政、金融];
学科分类号
0202 ;
摘要
Semi supervised learning has attracted attention of AI researchers in the recent past, especially after the advent of deep learning methods and their success in several real world applications. Most deep learning models require large amounts of labelled data, which is expensive to obtain. Fraud detection is a very important problem for several industries and large amount of data is often available. However, obtaining labelled data is cumbersome and hence semi-supervised learning is perfectly positioned to aid us in building robust and accurate supervised models. In this work, we consider different kinds of fraud detection paradigms and show that a self-training based semi-supervised learning approach can produce significant improvements over a model that has been training on a limited set of labelled data. We propose a novel self-training approach by using a guided sharpening technique using a pair of autoencoders which provide useful cues for incorporating unlabelled data in the training process. We conduct thorough experiments on three different real world databases and analysis to showcase the effectiveness of the approach. On the elliptic bitcoin fraud dataset, we show that utilizing unlabelled data improves the F-1 score of the model trained on limited labelled data by around 10%.
引用
收藏
页码:148 / 155
页数:8
相关论文
共 50 条
  • [31] A Theoretical Characterization of Semi-supervised Learning with Self-training for Gaussian Mixture Models
    Oymak, Samet
    Gulcu, Talha Cihad
    24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
  • [32] Semi-supervised Learning with Support Isolation by Small-Paced Self-Training
    Xie, Zheng
    Sun, Hui
    Li, Ming
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 9, 2023, : 10510 - 10518
  • [33] Semi-supervised Multitask Learning via Self-training and Maximum Entropy Discrimination
    Chao, Guoqing
    Sun, Shiliang
    NEURAL INFORMATION PROCESSING, ICONIP 2012, PT III, 2012, 7665 : 340 - 347
  • [34] Semi-supervised Object Detection with Adaptive Class-Rebalancing Self-Training
    Zhang, Fangyuan
    Pan, Tianxiang
    Wang, Bin
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 3252 - 3261
  • [35] Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting
    Liu, Hao
    Chen, Bin
    Wang, Bo
    Wu, Chunpeng
    Dai, Feng
    Wu, Peng
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 6569 - 6578
  • [36] Enhancing Semi-Supervised Learning With Concept Drift Detection and Self-Training: A Study on Classifier Diversity and Performance
    Perez, Jose L. M.
    Barros, Roberto S. M.
    Santos, Silas G. T. C.
    IEEE ACCESS, 2025, 13 : 24681 - 24697
  • [37] Self-training method based on GCN for semi-supervised short text classification
    Cui, Hongyan
    Wang, Gangkun
    Li, Yuanxin
    Welsch, Roy E.
    INFORMATION SCIENCES, 2022, 611 : 18 - 29
  • [38] A self-training hierarchical prototype-based approach for semi-supervised classification
    Gu, Xiaowei
    INFORMATION SCIENCES, 2020, 535 : 204 - 224
  • [39] Semi-supervised PCA-based face recognition using self-training
    Roli, Fabio
    Marcialis, Gian Luca
    STRUCTURAL, SYNTACTIC, AND STATISTICAL PATTERN RECOGNITION, PROCEEDINGS, 2006, 4109 : 560 - 568
  • [40] Improving semi-supervised self-training with embedded manifold transduction
    Tao, Ye
    Zhang, Duzhou
    Cheng, Shengjun
    Tang, Xianglong
    TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2018, 40 (02) : 363 - 374