31 citations · 78 across the 15 of their papers we have counts for
7 papers · 1 filter
Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
Xiangmeng Wang, Qian Li, Haiyang Xia +3
Heterophily is a prevalent property of real-world graphs and is well known to impair the performance of homophilic Graph Neural Networks (GNNs). Prior work has attempted to adapt G…
CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows
Tri Dung Duong, Qian Li, Guandong Xu
Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as ins…
Achieving Counterfactual Fairness with Imperfect Structural Causal Model
Tri Dung Duong, Qian Li, Guandong Xu
Counterfactual fairness alleviates the discrimination between the model prediction toward an individual in the actual world (observational data) and that in counterfactual world (i…
Generating Counterfactual Hard Negative Samples for Graph Contrastive Learning
Haoran Yang, Hongxu Chen, Sixiao Zhang +4
Graph contrastive learning has emerged as a powerful tool for unsupervised graph representation learning. The key to the success of graph contrastive learning is to acquire high-qu…
Deep Treatment-Adaptive Network for Causal Inference
Qian Li, Zhichao Wang, Shaowu Liu +2
Causal inference is capable of estimating the treatment effect (i.e., the causal effect of treatment on the outcome) to benefit the decision making in various domains. One fundamen…
Be Causal: De-biasing Social Network Confounding in Recommendation
Qian Li, Xiangmeng Wang, Guandong Xu
In recommendation systems, the existence of the missing-not-at-random (MNAR) problem results in the selection bias issue, degrading the recommendation performance ultimately. A com…
Causality-based Counterfactual Explanation for Classification Models
Tri Dung Duong, Qian Li, Guandong Xu
Counterfactual explanation is one branch of interpretable machine learning that produces a perturbation sample to change the model's original decision. The generated samples can ac…