Voucher abuse detection with prompt-based fine-tuning on graph neural networks
Voucher abuse detection is an important anomaly detection problem in E-commerce. While many GNN-based solutions have emerged, the supervised paradigm depends on a large quantity of labeled data. A popular alternative is to adopt self-supervised pre-training using label-free data, and further fine-tu...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8251 https://ink.library.smu.edu.sg/context/sis_research/article/9254/viewcontent/CIKM23_VPGNN.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-9254 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-92542023-11-10T09:04:35Z Voucher abuse detection with prompt-based fine-tuning on graph neural networks WEN, Zhihao FANG, Yuan LIU, Yihan GUO, Yang HAO, Shuji Voucher abuse detection is an important anomaly detection problem in E-commerce. While many GNN-based solutions have emerged, the supervised paradigm depends on a large quantity of labeled data. A popular alternative is to adopt self-supervised pre-training using label-free data, and further fine-tune on a downstream task with limited labels. Nevertheless, the "pre-train, fine-tune" paradigm is often plagued by the objective gap between pre-training and downstream tasks. Hence, we propose VPGNN, a prompt-based fine-tuning framework on GNNs for voucher abuse detection. We design a novel graph prompting function to reformulate the downstream task into a similar template as the pretext task in pre-training, thereby narrowing the objective gap. Extensive experiments on both proprietary and public datasets demonstrate the strength of VPGNN in both few-shot and semi-supervised scenarios. Moreover, an online deployment of VPGNN in a production environment shows a 23.4% improvement over two existing deployed models. 2023-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8251 info:doi/10.1145/3583780.3615505 https://ink.library.smu.edu.sg/context/sis_research/article/9254/viewcontent/CIKM23_VPGNN.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University anomaly detection graph neural networks pre-training prompt Artificial Intelligence and Robotics |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
anomaly detection graph neural networks pre-training prompt Artificial Intelligence and Robotics |
spellingShingle |
anomaly detection graph neural networks pre-training prompt Artificial Intelligence and Robotics WEN, Zhihao FANG, Yuan LIU, Yihan GUO, Yang HAO, Shuji Voucher abuse detection with prompt-based fine-tuning on graph neural networks |
description |
Voucher abuse detection is an important anomaly detection problem in E-commerce. While many GNN-based solutions have emerged, the supervised paradigm depends on a large quantity of labeled data. A popular alternative is to adopt self-supervised pre-training using label-free data, and further fine-tune on a downstream task with limited labels. Nevertheless, the "pre-train, fine-tune" paradigm is often plagued by the objective gap between pre-training and downstream tasks. Hence, we propose VPGNN, a prompt-based fine-tuning framework on GNNs for voucher abuse detection. We design a novel graph prompting function to reformulate the downstream task into a similar template as the pretext task in pre-training, thereby narrowing the objective gap. Extensive experiments on both proprietary and public datasets demonstrate the strength of VPGNN in both few-shot and semi-supervised scenarios. Moreover, an online deployment of VPGNN in a production environment shows a 23.4% improvement over two existing deployed models. |
format |
text |
author |
WEN, Zhihao FANG, Yuan LIU, Yihan GUO, Yang HAO, Shuji |
author_facet |
WEN, Zhihao FANG, Yuan LIU, Yihan GUO, Yang HAO, Shuji |
author_sort |
WEN, Zhihao |
title |
Voucher abuse detection with prompt-based fine-tuning on graph neural networks |
title_short |
Voucher abuse detection with prompt-based fine-tuning on graph neural networks |
title_full |
Voucher abuse detection with prompt-based fine-tuning on graph neural networks |
title_fullStr |
Voucher abuse detection with prompt-based fine-tuning on graph neural networks |
title_full_unstemmed |
Voucher abuse detection with prompt-based fine-tuning on graph neural networks |
title_sort |
voucher abuse detection with prompt-based fine-tuning on graph neural networks |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/8251 https://ink.library.smu.edu.sg/context/sis_research/article/9254/viewcontent/CIKM23_VPGNN.pdf |
_version_ |
1783955657766993920 |