Qiaoyu Tan

Unseen Anomaly Detection on Networks via Multi-Hypersphere Learning

2022 · Society for Industrial and Applied Mathematics eBooks

Network anomaly detection is a crucial task since a few anomalies can cause huge losses. Semi-supervised anomaly detection methods can effectively leverage a small number of labels as prior knowledge to enhance detection accuracy. But …

Towards Personalized Preprocessing Pipeline Search

2023 · arXiv (Cornell University)

Feature preprocessing, which transforms raw input features into numerical representations, is a crucial step in automated machine learning (AutoML) systems. However, the existing systems often have a very small search space for feature preprocessing with …

UniGLM: Training One Unified Language Model for Text-Attributed Graph Embedding

2024 · arXiv (Cornell University)

Representation learning on text-attributed graphs (TAGs), where nodes are represented by textual descriptions, is crucial for textual and relational knowledge systems and recommendation systems. Currently, state-of-the-art embedding methods for TAGs primarily focus on fine-tuning language …