11 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…
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…
A Novel Generative Model with Causality Constraint for Mitigating Biases in Recommender Systems
Jianfeng Deng, Qingfeng Chen, Debo Cheng +3
Accurately predicting counterfactual user feedback is essential for building effective recommender systems. However, latent confounding bias can obscure the true causal relationshi…
Mitigating Propensity Bias of Large Language Models for Recommender Systems
Guixian Zhang, Guan Yuan, Debo Cheng +3
The rapid development of Large Language Models (LLMs) creates new opportunities for recommender systems, especially by exploiting the side information (e.g., descriptions and analy…