A2TTA: Anchored-and-Agile Test-Time Adaptation for Evolving Traffic Sensor Networks

2026-07-28

AI Summary

This work addresses the degradation of prediction performance in traffic sensor networks caused by road network expansion and shifts in human mobility patterns. To tackle this challenge, the authors propose A2TTA, a novel test-time adaptation (TTA) framework that jointly handles topological structure expansion and multi-scale temporal distribution shifts—an approach not previously explored in TTA. The method formulates topological changes as a scalable output calibration problem and introduces a dual-path mechanism to decouple long-term global correction from short-term context-specific adaptation. Extensive experiments across ten real-world traffic networks demonstrate that A2TTA consistently and significantly improves prediction accuracy across diverse backbone models, datasets, and forecasting horizons, exhibiting both high efficiency and robust online adaptability.

Abstract

Traffic forecasting is important for efficient traffic management and route planning in smart cities. Existing traffic forecasting studies typically assume fixed sensor graphs, overlooking the continuous evolution of real-world traffic networks, e.g., ongoing road network construction and evolving human mobility patterns. These dynamic changes can substantially degrade conventional forecasting models, motivating test-time adaptation (TTA) to efficiently adapt pretrained models during deployment. However, applying TTA to evolving traffic sensor networks remains challenging in two aspects. First, topology expansion introduces new sensors and connections, continuously reshaping the sensor graph. Second, tem- poral shifts vary in time scale and stability, requiring differentiated adaptation to long-term and short-term shifts. In this study, we address these challenges by proposing A2TTA, an Anchored-and-Agile Test-Time Adaptation framework for evolving traffic sensor networks, which transforms topology-induced forecasting errors into an expandable output calibration problem and separates tem- poral adaptation into persistent global correction and agile context-specific specialization. By jointly addressing topology evolution and multi-scale temporal shifts, A2TTA enables efficient and robust adaptation to continuously evolving traffic environments. Extensive experiments on ten real-world traffic networks demonstrate that A2TTA consistently improves forecasting performance across different backbones, datasets, and prediction horizons. Our code is available in https://github.com/lixus7/A2TTA.

Problem

• traffic forecasting
• test-time adaptation
• evolving sensor networks
• topology expansion
• temporal shifts

Innovation

• Test-Time Adaptation
• Evolving Graph
• Traffic Forecasting
• Topology Expansion
• Multi-scale Temporal Shift