DOMINO: Domain-invariant Hyperdimensional Classification for Multi-Sensor Time Series Data

TL;DR

DOMINO introduces a hyperdimensional computing framework that effectively addresses distribution shift in multi-sensor time series classification, offering improved accuracy, robustness, and computational efficiency on edge devices.

Contribution

It presents a novel HDC-based method that dynamically filters domain-variant features, outperforming state-of-the-art DNNs in accuracy, speed, and robustness under challenging conditions.

Findings

Achieves 2.04% higher accuracy than SOTA DNNs.

Provides 16.34x faster training and 2.89x faster inference.

Offers 10.93x higher robustness to hardware noise.

Abstract

With the rapid evolution of the Internet of Things, many real-world applications utilize heterogeneously connected sensors to capture time-series information. Edge-based machine learning (ML) methodologies are often employed to analyze locally collected data. However, a fundamental issue across data-driven ML approaches is distribution shift. It occurs when a model is deployed on a data distribution different from what it was trained on, and can substantially degrade model performance. Additionally, increasingly sophisticated deep neural networks (DNNs) have been proposed to capture spatial and temporal dependencies in multi-sensor time series data, requiring intensive computational resources beyond the capacity of today's edge devices. While brain-inspired hyperdimensional computing (HDC) has been introduced as a lightweight solution for edge-based learning, existing HDCs are also vulnerable to the distribution shift challenge. In this paper, we propose DOMINO, a novel HDC learning framework addressing the distribution shift problem in noisy multi-sensor time-series data. DOMINO leverages efficient and parallel matrix operations on high-dimensional space to dynamically identify and filter out domain-variant dimensions. Our evaluation on a wide range of multi-sensor time series classification tasks shows that DOMINO achieves on average 2.04% higher accuracy than state-of-the-art (SOTA) DNN-based domain generalization techniques, and delivers 16.34x faster training and 2.89x faster inference. More importantly, DOMINO performs notably better when learning from partially labeled and highly imbalanced data, providing 10.93x higher robustness against hardware noises than SOTA DNNs.