Explainability Techniques for Graph Convolutional Networks
read the original abstract
Graph Networks are used to make decisions in potentially complex scenarios but it is usually not obvious how or why they made them. In this work, we study the explainability of Graph Network decisions using two main classes of techniques, gradient-based and decomposition-based, on a toy dataset and a chemistry task. Our study sets the ground for future development as well as application to real-world problems.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Aitchison Embeddings for Learning Compositional Graph Representations
Graph nodes are embedded as simplex compositions via ILR coordinates to yield intrinsically interpretable representations that preserve Aitchison geometry and enable subcompositional analysis.
-
A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring
A systematic method leveraging Weisfeiler-Leman coloring to mine class-discriminating motifs as proxy explanations, enabling the creation of the OpenGraphXAI benchmark suite from real-world datasets.
-
Estimating Subgraph Importance with Structural Prior Domain Knowledge
A label-free Group Lasso method estimates important subgraphs in pretrained GNNs by incorporating domain structural knowledge.
-
From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning
M2D distillation augments input graphs with model-derived features and structure, letting simple student GNNs match teacher performance while exposing mechanisms such as attention and fairness directly in the data.
-
TACENR: Task-Agnostic Contrastive Explanations for Node Representations
TACENR introduces a contrastive-learning method that identifies the most influential attribute, proximity, and structural features in node representations in a task-agnostic manner.
-
Explaining the Explainers in Graph Neural Networks: a Comparative Study
Benchmark study of ten GNN explainers on eight architectures and six datasets that isolates usable components and issues practical recommendations.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.