17 citations · 21 across the 4 of their papers we have counts for
5 papers
Toward a Causal Data Management Ecosystem for Decision Making and Agentic AI
Dazhuo Qiu, Yingli Zhou, Amedeo Pachera +2
Modern AI is no longer a single model but an ecosystem: classical ML predictors, deep and multimodal models, large language models, and agents, each trained and tuned over differen…
Finding Counterfactual Evidences for Node Classification
Dazhuo Qiu, Jinwen Chen, Arijit Khan +2
Counterfactual learning is emerging as an important paradigm, rooted in causality, which promises to alleviate common issues of graph neural networks (GNNs), such as fairness and i…
Interpreting Graph Inference with Skyline Explanations
Dazhuo Qiu, Haolai Che, Arijit Khan +1
Inference queries have been routinely issued to graph machine learning models such as graph neural networks (GNNs) for various network analytical tasks. Nevertheless, GNN outputs a…
Generating Robust Counterfactual Witnesses for Graph Neural Networks
Dazhuo Qiu, Mengying Wang, Arijit Khan +1
This paper introduces a new class of explanation structures, called robust counterfactual witnesses (RCWs), to provide robust, both counterfactual and factual explanations for grap…
View-based Explanations for Graph Neural Networks
Tingyang Chen, Dazhuo Qiu, Yinghui Wu +3
Generating explanations for graph neural networks (GNNs) has been studied to understand their behavior in analytical tasks such as graph classification. Existing approaches aim to…