FlowDistill: Scalable Traffic Flow Prediction via Distillation from LLMs

TL;DR

FlowDistill introduces a scalable, efficient traffic flow prediction method that distills knowledge from large language models into a lightweight model, outperforming existing approaches in accuracy and resource usage.

Contribution

The paper presents a novel knowledge distillation framework from LLMs to a compact model for traffic prediction, improving scalability and efficiency.

Findings

Outperforms state-of-the-art models in accuracy

Requires less training data and computational resources

Achieves lower memory usage and inference latency

Abstract

Accurate traffic flow prediction is vital for optimizing urban mobility, yet it remains difficult in many cities due to complex spatio-temporal dependencies and limited high-quality data. While deep graph-based models demonstrate strong predictive power, their performance often comes at the cost of high computational overhead and substantial training data requirements, making them impractical for deployment in resource-constrained or data-scarce environments. We propose the FlowDistill, a lightweight and scalable traffic prediction framework based on knowledge distillation from large language models (LLMs). In this teacher-student setup, a fine-tuned LLM guides a compact multi-layer perceptron (MLP) student model using a novel combination of the information bottleneck principle and teacher-bounded regression loss, ensuring the distilled model retains only essential and transferable knowledge. Spatial and temporal correlations are explicitly encoded to enhance the model's generalization across diverse urban settings. Despite its simplicity, FlowDistill consistently outperforms state-of-the-art models in prediction accuracy while requiring significantly less training data, and achieving lower memory usage and inference latency, highlighting its efficiency and suitability for real-world, scalable deployment.