# Graph Neural Networks Including Sparse Interpretability

arXiv: https://arxiv.org/abs/2007.00119 · HTML: https://mlsanity.com/paper/2007.00119/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2020.

## Built on by (most cited first, 13 of 13)

- [Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning](https://mlsanity.com/paper/2202.08816/) (2022)
- [A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics](https://mlsanity.com/paper/2207.12599/) (2022)
- [Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs](https://mlsanity.com/paper/2406.15156/) (2024)
- [Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective](https://mlsanity.com/paper/2502.02719/) (2025)
- [How Faithful are Self-Explainable GNNs?](https://mlsanity.com/paper/2308.15096/) (2023)
- [GNN Explanations that do not Explain and How to find Them](https://mlsanity.com/paper/2601.20815/) (2026)
- [Generating Human Understandable Explanations for Node Embeddings](https://mlsanity.com/paper/2406.07642/) (2024)
- [Aitchison Embeddings for Learning Compositional Graph Representations](https://mlsanity.com/paper/2605.00716/) (2026)
- [Adaptive Node Feature Selection For Graph Neural Networks](https://mlsanity.com/paper/2510.03096/) (2025)
- [Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls](https://mlsanity.com/paper/2602.21342/) (2026)
- [Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It](https://mlsanity.com/paper/2605.07527/) (2026)
- [Controllable GNN Explanations via Multi-Metric Preference Selection](https://mlsanity.com/paper/2609.32436/) (2026)
- [Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks](https://mlsanity.com/paper/2609.37972/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) are versatile, powerful machine learning methods that enable graph structure and feature representation learning, and have applications across many domains. For applications critically requiring interpretation, attention-based GNNs have been leveraged. However, these approaches either rely on specific model architectures or lack a joint consideration of graph structure and node features in their interpretation. Here we present a model-agnostic framework for interpreting important graph structure and node features, Graph neural networks Including SparSe inTerpretability (GISST). With any GNN model, GISST combines an attention mechanism and sparsity regularization to yield an important subgraph and node feature subset related to any graph-based task. Through a single self-attention layer, a GISST model learns an importance probability for each node feature and edge in the input graph. By including these importance probabilities in the model loss function, the probabilities are optimized end-to-end and tied to the task-specific performance. Furthermore, GISST sparsifies these importance probabilities with entropy and L1 regularization to reduce noise in the input graph topology and node features. Our GISST models achieve superior node feature and edge explanation precision in synthetic datasets, as compared to alternative interpretation approaches. Moreover, our GISST models are able to identify important graph structure in real-world datasets. We demonstrate in theory that edge feature importance and multiple edge types can be considered by incorporating them into the GISST edge probability computation. By jointly accounting for topology, node features, and edge features, GISST inherently provides simple and relevant interpretations for any GNN models and tasks.