A Novel Hyperdimensional Computing Framework for Online Time Series Forecasting on the Edge

TL;DR

This paper introduces TSF-HD, a hyperdimensional computing framework that enables fast, efficient, and adaptive online time series forecasting by mapping nonlinear data into high-dimensional spaces for linear prediction.

Contribution

The paper presents a novel hyperdimensional approach for online time series forecasting that effectively adapts to data shifts and reduces inference latency.

Findings

Outperforms state-of-the-art methods in accuracy

Reduces inference latency significantly

Effectively adapts to distribution shifts

Abstract

In recent years, both online and offline deep learning models have been developed for time series forecasting. However, offline deep forecasting models fail to adapt effectively to changes in time-series data, while online deep forecasting models are often expensive and have complex training procedures. In this paper, we reframe the online nonlinear time-series forecasting problem as one of linear hyperdimensional time-series forecasting. Nonlinear low-dimensional time-series data is mapped to high-dimensional (hyperdimensional) spaces for linear hyperdimensional prediction, allowing fast, efficient and lightweight online time-series forecasting. Our framework, TSF-HD, adapts to time-series distribution shifts using a novel co-training framework for its hyperdimensional mapping and its linear hyperdimensional predictor. TSF-HD is shown to outperform the state of the art, while having reduced inference latency, for both short-term and long-term time series forecasting. Our code is publicly available at http://github.com/tsfhd2024/tsf-hd.git