From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning
For GNN researchers and practitioners, M2D provides a new way to achieve architectural transparency and understand performance gaps between models, though it is an incremental step in explainability.
M2D distillation transfers model complexity from GNNs to graph data, enabling a simple student model to match teacher performance while revealing mechanisms like fairness and attention in an interpretable way.
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.