7 papers
Disentangled Instrumental Variables for Causal Inference with Networked Observational Data
Zhirong Huang, Debo Cheng, Guixian Zhang +3
Instrumental variables (IVs) are crucial for addressing unobservable confounders, yet their stringent exogeneity assumptions pose significant challenges in networked data. Existing…
DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detection
Qingfeng Chen, Haojin Zeng, Jingyi Jie +2
With the rapid growth of graph-structured data in critical domains, unsupervised graph-level anomaly detection (UGAD) has become a pivotal task. UGAD seeks to identify entire graph…
Toward Fair Graph Neural Networks Via Dual-Teacher Knowledge Distillation
Chengyu Li, Debo Cheng, Guixian Zhang +2
Graph Neural Networks (GNNs) have demonstrated strong performance in graph representation learning across various real-world applications. However, they often produce biased predic…
Harnessing LLM for Noise-Robust Cognitive Diagnosis in Web-Based Intelligent Education Systems
Guixian Zhang, Guan Yuan, Ziqi Xu +4
Cognitive diagnostics in the Web-based Intelligent Education System (WIES) aims to assess students' mastery of knowledge concepts from heterogeneous, noisy interactions. Recent wor…
Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems
Zhirong Huang, Debo Cheng, Jiuyong Li +3
It is often challenging to identify a valid instrumental variable (IV), although the IV methods have been regarded as effective tools of addressing the confounding bias introduced…
Efficient Adaptive Label Refinement for Label Noise Learning
Wenzhen Zhang, Debo Cheng, Guangquan Lu +3
Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined crit…