2 citations · 2 across the 8 of their papers we have counts for
8 papers
Uncertainty Quantification on Graph Learning: A Survey
Chao Chen, Chenghua Guo, Rui Xu +6
Graphical models have demonstrated their exceptional capabilities across numerous applications. However, their performance, confidence, and trustworthiness are often limited by the…
Robust Ranking Explanations
Chao Chen, Chenghua Guo, Guixiang Ma +3
Robust explanations of machine learning models are critical to establish human trust in the models. Due to limited cognition capability, most humans can only interpret the top few…
Provable Robust Saliency-based Explanations
Chao Chen, Chenghua Guo, Rufeng Chen +5
To foster trust in machine learning models, explanations must be faithful and stable for consistent insights. Existing relevant works rely on the distance for stability as…
Multi-objective Explanations of GNN Predictions
Yifei Liu, Chao Chen, Yazheng Liu +2
Graph Neural Network (GNN) has achieved state-of-the-art performance in various high-stake prediction tasks, but multiple layers of aggregations on graphs with irregular structures…
Self-learn to Explain Siamese Networks Robustly
Chao Chen, Yifan Shen, Guixiang Ma +4
Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and i…
Rigorous Explanation of Inference on Probabilistic Graphical Models
Yifei Liu, Chao Chen, Xi Zhang +1
Probabilistic graphical models, such as Markov random fields (MRF), exploit dependencies among random variables to model a rich family of joint probability distributions. Sophistic…
Scalable Explanation of Inferences on Large Graphs
Chao Chen, Yifei Liu, Xi Zhang +1
Probabilistic inferences distill knowledge from graphs to aid human make important decisions. Due to the inherent uncertainty in the model and the complexity of the knowledge, it i…
The Most Persistent Soft-Clique in a Set of Sampled Graphs
Novi Quadrianto, Chao Chen, Christoph Lampert
When searching for characteristic subpatterns in potentially noisy graph data, it appears self-evident that having multiple observations would be better than having just one. Howev…