Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AutoFed: Manual-Free Federated Traffic Prediction via Personalized Prompt

Zijian Zhao, Yitong Shang, Sen Li

TL;DR

AutoFed tackles privacy-preserving traffic prediction under non-IID client data by coupling a locally optimized Personalized Predictor with a Federated Representor that outputs a global prompt guiding decoding. By distilling local patterns into a compact prefix through a denoising encoder, adaptive graph encoder, and FedBN-style adapter, AutoFed enables cross-client knowledge transfer without manual hyperparameter tuning. Empirical results on real-world Travel Demand and Traffic Flow datasets show state-of-the-art or competitive performance with lower reliance on dataset-specific tuning and reduced communication overhead. The approach offers practical, scalable deployment for ITS applications where data privacy and heterogeneity are major concerns.

Abstract

Accurate traffic prediction is essential for Intelligent Transportation Systems, including ride-hailing, urban road planning, and vehicle fleet management. However, due to significant privacy concerns surrounding traffic data, most existing methods rely on local training, resulting in data silos and limited knowledge sharing. Federated Learning (FL) offers an efficient solution through privacy-preserving collaborative training; however, standard FL struggles with the non-independent and identically distributed (non-IID) problem among clients. This challenge has led to the emergence of Personalized Federated Learning (PFL) as a promising paradigm. Nevertheless, current PFL frameworks require further adaptation for traffic prediction tasks, such as specialized graph feature engineering, data processing, and network architecture design. A notable limitation of many prior studies is their reliance on hyper-parameter optimization across datasets-information that is often unavailable in real-world scenarios-thus impeding practical deployment. To address this challenge, we propose AutoFed, a novel PFL framework for traffic prediction that eliminates the need for manual hyper-parameter tuning. Inspired by prompt learning, AutoFed introduces a federated representor that employs a client-aligned adapter to distill local data into a compact, globally shared prompt matrix. This prompt then conditions a personalized predictor, allowing each client to benefit from cross-client knowledge while maintaining local specificity. Extensive experiments on real-world datasets demonstrate that AutoFed consistently achieves superior performance across diverse scenarios. The code of this paper is provided at https://github.com/RS2002/AutoFed .

AutoFed: Manual-Free Federated Traffic Prediction via Personalized Prompt

TL;DR

AutoFed tackles privacy-preserving traffic prediction under non-IID client data by coupling a locally optimized Personalized Predictor with a Federated Representor that outputs a global prompt guiding decoding. By distilling local patterns into a compact prefix through a denoising encoder, adaptive graph encoder, and FedBN-style adapter, AutoFed enables cross-client knowledge transfer without manual hyperparameter tuning. Empirical results on real-world Travel Demand and Traffic Flow datasets show state-of-the-art or competitive performance with lower reliance on dataset-specific tuning and reduced communication overhead. The approach offers practical, scalable deployment for ITS applications where data privacy and heterogeneity are major concerns.

Abstract

Accurate traffic prediction is essential for Intelligent Transportation Systems, including ride-hailing, urban road planning, and vehicle fleet management. However, due to significant privacy concerns surrounding traffic data, most existing methods rely on local training, resulting in data silos and limited knowledge sharing. Federated Learning (FL) offers an efficient solution through privacy-preserving collaborative training; however, standard FL struggles with the non-independent and identically distributed (non-IID) problem among clients. This challenge has led to the emergence of Personalized Federated Learning (PFL) as a promising paradigm. Nevertheless, current PFL frameworks require further adaptation for traffic prediction tasks, such as specialized graph feature engineering, data processing, and network architecture design. A notable limitation of many prior studies is their reliance on hyper-parameter optimization across datasets-information that is often unavailable in real-world scenarios-thus impeding practical deployment. To address this challenge, we propose AutoFed, a novel PFL framework for traffic prediction that eliminates the need for manual hyper-parameter tuning. Inspired by prompt learning, AutoFed introduces a federated representor that employs a client-aligned adapter to distill local data into a compact, globally shared prompt matrix. This prompt then conditions a personalized predictor, allowing each client to benefit from cross-client knowledge while maintaining local specificity. Extensive experiments on real-world datasets demonstrate that AutoFed consistently achieves superior performance across diverse scenarios. The code of this paper is provided at https://github.com/RS2002/AutoFed .
Paper Structure (19 sections, 5 equations, 3 figures, 3 tables, 1 algorithm)

This paper contains 19 sections, 5 equations, 3 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Traffic Prediction
  4. Federated Learning
  5. Prompt Learning
  6. Methodology
  7. Problem Setup
  8. Method Overview
  9. Personalized Predictor
  10. Federated Representor
  11. Training Process
  12. Experiment
  13. Experiment Setup
  14. Experiment Results
  15. Discussions and Analysis
  16. ...and 4 more sections

Figures (3)

  • Figure 1: Network Architecture: The network consists of the PP and FR. PP utilizes a graph time series network with an encoder-decoder structure. FR employs an AE-based denoiser for robust feature extraction, a graph time series encoder for feature compression, and an client-aligned adapter for transferring local representations to global representations, providing a guided prompt matrix for the decoder in PP. In the figure, only the modules with the "earth" icon are shared among clients.
  • Figure 2: Comparison Between Local Representation and Global Representation
  • Figure 3: Training Process: This figure shows the change of different metrics in valid set during training.