From GNNs to Symbolic Surrogates via Kolmogorov-Arnold Networks for Delay Prediction

TL;DR

This paper introduces a novel approach combining GNNs, Kolmogorov-Arnold Networks, and symbolic regression to improve delay prediction in communication networks, emphasizing efficiency, transparency, and lightweight deployment.

Contribution

It proposes FlowKANet with KAN layers and a symbolic distillation method, advancing neural network efficiency and interpretability for network delay prediction.

Findings

KAN layers offer a good balance between efficiency and accuracy

Symbolic surrogates enable lightweight and transparent models

FlowKANet maintains competitive performance with fewer parameters

Abstract

Accurate prediction of flow delay is essential for optimizing and managing modern communication networks. We investigate three levels of modeling for this task. First, we implement a heterogeneous GNN with attention-based message passing, establishing a strong neural baseline. Second, we propose FlowKANet in which Kolmogorov-Arnold Networks replace standard MLP layers, reducing trainable parameters while maintaining competitive predictive performance. FlowKANet integrates KAMP-Attn (Kolmogorov-Arnold Message Passing with Attention), embedding KAN operators directly into message-passing and attention computation. Finally, we distill the model into symbolic surrogate models using block-wise regression, producing closed-form equations that eliminate trainable weights while preserving graph-structured dependencies. The results show that KAN layers provide a favorable trade-off between efficiency and accuracy and that symbolic surrogates emphasize the potential for lightweight deployment and enhanced transparency.