Qiang Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qiang Huang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Yi Chang
Jilin University, China
4 shared publications - Huiyan Sun
School of Artificial Intelligence, Jilin University, Changchun, China
3 shared publications - Jing Ma
Case Western Reserve University
2 shared publications - Jundong Li
University of Virginia
2 shared publications - Makoto Yamada
Okinawa Institute of Science and Technology
2 shared publications Dawei Yin
1 shared publication
Latest Publications
- 15 March 2026
- Published by Elsevier in Artificial Intelligence
- Vol. 355
Environment promoted invariant information learning for graph out-of-distribution generalization
- 15 March 2026
- Published by Elsevier in Artificial Intelligence
- Vol. 355
Environment promoted invariant information learning for graph out-of-distribution generalization
- 11 July 2024
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 38 (6) , 3783-3804
De-confounding representation learning for counterfactual inference on continuous treatment via generative adversarial network
- 11 July 2024
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 38 (6) , 3783-3804
De-confounding representation learning for counterfactual inference on continuous treatment via generative adversarial network
- Open Access
- 9 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (3) , 1-21
Modeling Interference for Individual Treatment Effect Estimation from Networked Observational Data
Estimating individual treatment effect (ITE) from observational data has attracted great interest in recent years, which plays a crucial role in decision-making across many high-impact domains such as economics, medicine, and e-commerce. Most existing studies of ITE estimation assume that different units at play are independent and do not influence each other. However, many social science experiments have shown that there often exist different levels of interactions between units in observational data, especially in a networked environment. As a result, the treatment assignment of one unit can affect the outcome of other units connected to it in the network, which is referred to as the interference or spillover effect . In this article, we study an important problem of ITE estimation from networked observational data by modeling the interference between different units and provide a principled framework to support such study. Methodologically, we propose a novel framework, SPNet , that first captures the influence of hidden confounders with the aid of graph convolutional network and then models the interference by introducing an environment summary variable and developing a masked attention mechanism. Experimental evaluations on several semi-synthetic datasets based on real-world networks corroborate the superiority of our proposed framework over state-of-the-art individual treatment effect estimation methods.
- 9 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (3) , 1-21
Open AccessModeling Interference for Individual Treatment Effect Estimation from Networked Observational Data
Estimating individual treatment effect (ITE) from observational data has attracted great interest in recent years, which plays a crucial role in decision-making across many high-impact domains such as economics, medicine, and e-commerce. Most existing studies of ITE estimation assume that different units at play are independent and do not influence each other. However, many social science experiments have shown that there often exist different levels of interactions between units in observational data, especially in a networked environment. As a result, the treatment assignment of one unit can affect the outcome of other units connected to it in the network, which is referred to as the interference or spillover effect . In this article, we study an important problem of ITE estimation from networked observational data by modeling the interference between different units and provide a principled framework to support such study. Methodologically, we propose a novel framework, SPNet , that first captures the influence of hidden confounders with the aid of graph convolutional network and then models the interference by introducing an environment summary variable and developing a masked attention mechanism. Experimental evaluations on several semi-synthetic datasets based on real-world networks corroborate the superiority of our proposed framework over state-of-the-art individual treatment effect estimation methods.
- 17 March 2023
- Published by Springer Nature
- p. 400-417
SemiITE: Semi-supervised Individual Treatment Effect Estimation via Disagreement-Based Co-training
- 17 March 2023
- Published by Springer Nature
- p. 400-417
SemiITE: Semi-supervised Individual Treatment Effect Estimation via Disagreement-Based Co-training
- Top Cited Papers
- 30 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (7) , 6968-6972
GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
Graph structured data has wide applicability in various domains such as physics, chemistry, biology, computer vision, and social networks, to name a few. Recently, graph neural networks (GNN) were shown to be successful in effectively representing graph structured data because of their good performance and generalization ability. However, explaining the effectiveness of GNN models is a challenging task because of the complex nonlinear transformations made over the iterations. In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method. GraphLIME is a generic GNN-model explanation framework that learns a nonlinear interpretable model locally in the subgraph of the node being explained. Through experiments on two real-world datasets, the explanations of GraphLIME are found to be of extraordinary degree and more descriptive in comparison to the existing explanation methods.
- 30 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (7) , 6968-6972
Top Cited PapersGraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
Graph structured data has wide applicability in various domains such as physics, chemistry, biology, computer vision, and social networks, to name a few. Recently, graph neural networks (GNN) were shown to be successful in effectively representing graph structured data because of their good performance and generalization ability. However, explaining the effectiveness of GNN models is a challenging task because of the complex nonlinear transformations made over the iterations. In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method. GraphLIME is a generic GNN-model explanation framework that learns a nonlinear interpretable model locally in the subgraph of the node being explained. Through experiments on two real-world datasets, the explanations of GraphLIME are found to be of extraordinary degree and more descriptive in comparison to the existing explanation methods.
- Open Access
GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
Graph structured data has wide applicability in various domains such as physics, chemistry, biology, computer vision, and social networks, to name a few. Recently, graph neural networks (GNN) were shown to be successful in effectively representing graph structured data because of their good performance and generalization ability. GNN is a deep learning based method that learns a node representation by combining specific nodes and the structural/topological information of a graph. However, like other deep models, explaining the effectiveness of GNN models is a challenging task because of the complex nonlinear transformations made over the iterations. In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method. GraphLIME is a generic GNN-model explanation framework that learns a nonlinear interpretable model locally in the subgraph of the node being explained. More specifically, to explain a node, we generate a nonlinear interpretable model from its $N$-hop neighborhood and then compute the K most representative features as the explanations of its prediction using HSIC Lasso. Through experiments on two real-world datasets, the explanations of GraphLIME are found to be of extraordinary degree and more descriptive in comparison to the existing explanation methods.
Open AccessGraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
Graph structured data has wide applicability in various domains such as physics, chemistry, biology, computer vision, and social networks, to name a few. Recently, graph neural networks (GNN) were shown to be successful in effectively representing graph structured data because of their good performance and generalization ability. GNN is a deep learning based method that learns a node representation by combining specific nodes and the structural/topological information of a graph. However, like other deep models, explaining the effectiveness of GNN models is a challenging task because of the complex nonlinear transformations made over the iterations. In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method. GraphLIME is a generic GNN-model explanation framework that learns a nonlinear interpretable model locally in the subgraph of the node being explained. More specifically, to explain a node, we generate a nonlinear interpretable model from its $N$-hop neighborhood and then compute the K most representative features as the explanations of its prediction using HSIC Lasso. Through experiments on two real-world datasets, the explanations of GraphLIME are found to be of extraordinary degree and more descriptive in comparison to the existing explanation methods.