GraphNNK - Graph Classification and Interpretability

2025-11-25

Telecommunications Forum

AI Summary

This work proposes a novel approach to graph classification by replacing the conventional parameterized classifier—such as a linear Softmax layer—in graph neural networks (GNNs) with non-negative kernel regression (NNK). Instead of relying on learnable parameters, the method constructs predictions via convex combinations of embeddings from similar training samples, effectively performing interpolation in the embedding space. This substitution not only enhances model interpretability by grounding predictions in actual training instances but also offers stronger theoretical guarantees for generalization. By eliminating the need for additional trainable parameters in the classification head, the approach provides a transparent and efficient mechanism that maintains predictive performance while improving the explainability and robustness of GNN-based graph classification.

Technology Category

Machine Learning: Graph-based Machine LearningReasoning under Uncertainty: Graphical ModelsData Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsUser Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

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.

Problem

• Graph Neural Networks
• Interpretability
• Graph Classification
• Generalization
• Parametric Classifiers

Innovation

• Graph Neural Networks
• Non-Negative Kernel Regression
• Interpretability
• Graph Classification
• Convex Combination