8 papers
FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detection
Wenxin Zhang, Ding Xu, Guangzhen Yao +6
Time series anomaly detection is critical for system monitoring and risk identification, across various domains, such as finance and healthcare. However, for most reconstruction-ba…
Addressing Noise and Stochasticity in Fraud Detection for Service Networks
Wenxin Zhang, Ding Xu, Xi Xuan +5
Fraud detection is crucial in social service networks to maintain user trust and improve service network security. Existing spectral graph-based methods address this challenge by l…
DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection
Wenxin Zhang, Xiaojian Lin, Wenjun Yu +7
Time series anomaly detection holds notable importance for risk identification and fault detection across diverse application domains. Unsupervised learning methods have become pop…
Dual-channel Heterophilic Message Passing for Graph Fraud Detection
Wenxin Zhang, Jingxing Zhong, Guangzhen Yao +4
Fraudulent activities have significantly increased across various domains, such as e-commerce, online review platforms, and social networks, making fraud detection a critical task.…
Dual Boost-Driven Graph-Level Clustering Network
John Smith, Wenxuan Tu, Junlong Wu +10
Graph-level clustering remains a pivotal yet formidable challenge in graph learning. Recently, the integration of deep learning with representation learning has demonstrated notabl…
MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction
Xuyin Qi, Zeyu Zhang, Huazhan Zheng +19
Bone density prediction via CT scans to estimate T-scores is crucial, providing a more precise assessment of bone health compared to traditional methods like X-ray bone density tes…