EPS
← All batches·2605.06814

From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning

topic: general_aitop score: 50released: 2026-05-11first surfaced: 2026-05-11arXivPDFnew_research2026-05-11

Authors: Debolina Halder Lina, Arlei Silva

arXiv · PDF

Summary

The authors propose a new framework for making graph neural networks (GNNs) more transparent by moving complexity out of the model architecture and into the data itself. They "distill" a complex teacher GNN into an augmented graph with enriched features and structure, so that a simple student model can match the teacher's performance on this new graph. This lets humans inspect what the complex model was doing by looking at the augmented data rather than reverse-engineering opaque model internals.

Main takeaways:

  • Standard GNN explainability methods highlight important nodes or edges for individual predictions, but don't explain why one architecture outperforms another.
  • Model-to-Data (M2D) distillation transfers architectural advantages (like attention mechanisms or fairness constraints) into visible graph structure and features.
  • A simple student GNN trained on the M2D-augmented graph matches the teacher's performance, making the learned behavior interpretable.
  • The approach reveals mechanisms like attention-based aggregation by materializing them as changes in the graph topology or features.

Relevance

Not directly related to my persona/midtraining work, but the conceptual idea of "materializing model behavior into interpretable data" loosely parallels my goal of finding prompts that correspond to fine-tuning or steering vectors — both are about making implicit model knowledge explicit and inspectable.

Abstract

arXiv:2605.06814v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) achieve high performance but can be opaque to humans, making it difficult to understand and compare the many proposed architectures. While existing explainability methods attribute individual predictions to nodes, edges, or features, they do not provide architectural transparency or explain the fundamental performance gap between simple and more complex models. To address this limitation, we introduce Model-to-Data (M2D) distillation, a new framework that increases transparency by transferring model complexity into the data space. M2D distills the teacher model into an augmented graph with enriched features and structure, enabling a simple student to match the teacher's performance. By materializing model behavior in the data, our approach allows humans to inspect architectural advantages directly. We show that M2D reveals underlying mechanisms such as fairness objectives and attention-based aggregation in an interpretable way, enhancing GNN transparency while preserving performance.