Graph Neural Networks (GNNs) have become a standard approach for learning from graph-structured data. However, their reliance on parametric classifiers (most often linear softmax layers) limits interpretability and sometimes hinders generalization. Recent work on interpolation-based methods, particularly Non-Negative Kernel regression (NNK), has demonstrated that predictions can be expressed as convex combinations of similar training examples in the embedding space, yielding both theoretical results and interpretable explanations.
@article{arxiv.2602.00753,
title = {GraphNNK -- Graph Classification and Interpretability},
author = {Zeljko Bolevic and Milos Brajovic and Isidora Stankovic and Ljubisa Stankovic},
journal= {arXiv preprint arXiv:2602.00753},
year = {2026}
}