Optimal Transport Prototypes and Symbolic Logic Combination for Self-Explainable Graph Neural Networks

Abstract

Graph Neural Networks achieve strong performance across diverse graph-based tasks, but their black-box nature remains a major obstacle in domains where interpretability is crucial. Prototype-based self-explainable GNNs mitigate this issue by grounding predictions in comparison with learned patterns. However, existing methods either restrict prototypes to training subgraphs, limiting expressiveness, or learn latent prototypes that lack interpretable counterparts in graph space. We introduce GELATO (Graph Explainability via Logic And Transport Optimization), a hybrid self-explainable graph classifier that integrates optimal transport, prototype grounding, and symbolic logic to produce faithful and human-readable explanations. We learn prototypes as point clouds in the embedding space and compare them to input graphs using partial optimal transport. To recover semantic meaning in graph space, each prototype point is anchored to a representative ego-network extracted from the training graphs. These similarity scores are then processed by a transparent logic layer that distills the model decisions into human-interpretable logical rules. Experiments on molecular and synthetic benchmarks show competitive predictive performance while producing interpretable, example-based explanations grounded in real graph structures.

Resources

Citation

@inproceedings{vincent2026gelato,
  title={Optimal Transport Prototypes and Symbolic Logic Combination for Self-Explainable Graph Neural Networks},
  author={Vincent, Elouan and Perez, Julien and Plantevit, Marc and Robardet, Celine},
  booktitle={ECML PKDD},
  year={2026}
}