Concept-based models can use controlled 'benign' information leakage to remain accurate and intervenable under real-world concept incompleteness by reframing their training objective.
Gcexplainer: Human-in- the-loop concept-based explanations for graph neural networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Concept Graph Convolutions perform message passing on node concepts to increase interpretability of graph neural networks without losing task performance.
A new semi-supervised hypergraph Concept Bottleneck Model framework improves label efficiency and interpretability for medical image diagnosis on PAS ultrasound, breast ultrasound, and SkinCon datasets.
AIM is a new evaluation framework for explainability in GNNs that combines accuracy, instance-level, and model-level measures, applied to graph kernel networks to create an improved model xGKN.
Subgraph Concept Network is a new GNN architecture that distills meaningful concepts at node, subgraph, and graph levels via soft clustering to improve explainability while maintaining competitive accuracy.
citing papers explorer
-
In Defense of Information Leakage in Concept-based Models
Concept-based models can use controlled 'benign' information leakage to remain accurate and intervenable under real-world concept incompleteness by reframing their training objective.
-
Concept Graph Convolutions: Message Passing in the Concept Space
Concept Graph Convolutions perform message passing on node concepts to increase interpretability of graph neural networks without losing task performance.
-
Learning Label-Efficient Interpretable Medical Image Diagnosis via Semi-supervised Hypergraph Concept Bottleneck Model
A new semi-supervised hypergraph Concept Bottleneck Model framework improves label efficiency and interpretability for medical image diagnosis on PAS ultrasound, breast ultrasound, and SkinCon datasets.
-
AIMing for Standardised Explainability Evaluation in GNNs: A Framework and Case Study on Graph Kernel Networks
AIM is a new evaluation framework for explainability in GNNs that combines accuracy, instance-level, and model-level measures, applied to graph kernel networks to create an improved model xGKN.
-
Subgraph Concept Networks: Concept Levels in Graph Classification
Subgraph Concept Network is a new GNN architecture that distills meaningful concepts at node, subgraph, and graph levels via soft clustering to improve explainability while maintaining competitive accuracy.