SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer

TL;DR

This paper introduces SSMT, a novel meta-transfer learning approach that enables few-shot traffic forecasting using only data from a single source city, leveraging memory-augmented attention and meta-positional encoding to improve predictions in data-scarce target cities.

Contribution

The paper proposes SSMT, a single-source meta-transfer learning method that effectively transfers knowledge for traffic forecasting in data-scarce cities, reducing reliance on multi-city data collection.

Findings

Outperforms existing methods on five real-world datasets.

Effectively leverages single-source data for few-shot traffic prediction.

Utilizes memory-augmented attention and meta-positional encoding for improved accuracy.

Abstract

Traffic forecasting in Intelligent Transportation Systems (ITS) is vital for intelligent traffic prediction. Yet, ITS often relies on data from traffic sensors or vehicle devices, where certain cities might not have all those smart devices or enabling infrastructures. Also, recent studies have employed meta-learning to generalize spatial-temporal traffic networks, utilizing data from multiple cities for effective traffic forecasting for data-scarce target cities. However, collecting data from multiple cities can be costly and time-consuming. To tackle this challenge, we introduce Single Source Meta-Transfer Learning (SSMT) which relies only on a single source city for traffic prediction. Our method harnesses this transferred knowledge to enable few-shot traffic forecasting, particularly when the target city possesses limited data. Specifically, we use memory-augmented attention to store the heterogeneous spatial knowledge from the source city and selectively recall them for the data-scarce target city. We extend the idea of sinusoidal positional encoding to establish meta-learning tasks by leveraging diverse temporal traffic patterns from the source city. Moreover, to capture a more generalized representation of the positions we introduced a meta-positional encoding that learns the most optimal representation of the temporal pattern across all the tasks. We experiment on five real-world benchmark datasets to demonstrate that our method outperforms several existing methods in time series traffic prediction.