# Learning Accurate, Efficient, and Interpretable MLPs on Multiplex Graphs via Node-wise Multi-View Ensemble Distillation

arXiv: https://arxiv.org/abs/2502.05864 · HTML: https://mlsanity.com/paper/2502.05864/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Graph neural network distillation, one of 12 directions in Knowledge distillation.
- First posted on arXiv 9 Feb 2025.

## Placed in

- Knowledge distillation / [Graph neural network distillation](https://mlsanity.com/distill/graph-neural-network-distillation/)

## Built on by (most cited first, 1 of 1)

- [Mitigating Homophily Disparity in Graph Anomaly Detection: A Scalable and Adaptive Approach](https://mlsanity.com/paper/2603.08137/) (2026)

## Abstract (arXiv)

Multiplex graphs, with multiple edge types (graph views) among common nodes, provide richer structural semantics and better modeling capabilities. Multiplex Graph Neural Networks (MGNNs), typically comprising view-specific GNNs and a multi-view integration layer, have achieved advanced performance in various downstream tasks. However, their reliance on neighborhood aggregation poses challenges for deployment in latency-sensitive applications. Motivated by recent GNN-to-MLP knowledge distillation frameworks, we propose Multiplex Graph-Free Neural Networks (MGFNN and MGFNN+) to combine MGNNs' superior performance and MLPs' efficient inference via knowledge distillation. MGFNN directly trains student MLPs with node features as input and soft labels from teacher MGNNs as targets. MGFNN+ further employs a low-rank approximation-based reparameterization to learn node-wise coefficients, enabling adaptive knowledge ensemble from each view-specific GNN. This node-wise multi-view ensemble distillation strategy allows student MLPs to learn more informative multiplex semantic knowledge for different nodes. Experiments show that MGFNNs achieve average accuracy improvements of about 10% over vanilla MLPs and perform comparably or even better to teacher MGNNs (accurate); MGFNNs achieve a 35.40×-89.14× speedup in inference over MGNNs (efficient); MGFNN+ adaptively assigns different coefficients for multi-view ensemble distillation regarding different nodes (interpretable).