5 papers · 1 filter
FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction
Kunyu Ni, Lei Cao, Jie He +4
Data preparation pipelines improve data quality in machine learning by transforming raw tables into learning-ready data through sequential cleaning and feature transformation opera…
ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion
Xiang Li, Jianpeng Qi, Haobing Liu +6
Graph Neural Networks (GNNs) have demonstrated impressive performance across diverse graph-based tasks by leveraging message passing to capture complex node relationships. However,…
Multi-Channel Hypergraph Contrastive Learning for Matrix Completion
Xiang Li, Changsheng Shui, Zhongying Zhao +2
Rating is a typical user explicit feedback that visually reflects how much a user likes a related item. The (rating) matrix completion is essentially a rating prediction process, w…
UMGAD: Unsupervised Multiplex Graph Anomaly Detection
Xiang Li, Jianpeng Qi, Zhongying Zhao +4
Graph anomaly detection (GAD) is a critical task in graph machine learning, with the primary objective of identifying anomalous nodes that deviate significantly from the majority.…
Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecasting
Lingxiao Cao, Bin Wang, Guiyuan Jiang +2
Traffic prediction is critical for optimizing travel scheduling and enhancing public safety, yet the complex spatial and temporal dynamics within traffic data present significant c…