Quantized symbolic time series approximation
Erin Carson, Xinye Chen, Cheng Kang
TL;DR
QABBA advances symbolic time-series representation by integrating quantization into ABBA to dramatically reduce storage while preserving reconstruction quality and speed. It offers a theoretical bound on quantization-induced error and practical guidance for bit-width selection, backed by extensive experiments on synthetic, UCR, and UEA datasets. When paired with large language models for time-series regression, QABBA enables embedding-free finetuning and achieves competitive or state-of-the-art results on the Monash regression tasks. The approach broadens the utility of symbolic time-series methods for hardware-efficient pipelines and LLM-enabled analytics, with substantial empirical support and clear directions for future work in quantization-aware learning and larger-scale applications.
Abstract
Time series are ubiquitous in numerous science and engineering domains, e.g., signal processing, bioinformatics, and astronomy. Previous work has verified the efficacy of symbolic time series representation in a variety of engineering applications due to its storage efficiency and numerosity reduction. The most recent symbolic aggregate approximation technique, ABBA, has been shown to preserve essential shape information of time series and improve downstream applications, e.g., neural network inference regarding prediction and anomaly detection in time series. Motivated by the emergence of high-performance hardware which enables efficient computation for low bit-width representations, we present a new quantization-based ABBA symbolic approximation technique, QABBA, which exhibits improved storage efficiency while retaining the original speed and accuracy of symbolic reconstruction. We prove an upper bound for the error arising from quantization and discuss how the number of bits should be chosen to balance this with other errors. An application of QABBA with large language models (LLMs) for time series regression is also presented, and its utility is investigated. By representing the symbolic chain of patterns on time series, QABBA not only avoids the training of embedding from scratch, but also achieves a new state-of-the-art on Monash regression dataset. The symbolic approximation to the time series offers a more efficient way to fine-tune LLMs on the time series regression task which contains various application domains. We further present a set of extensive experiments performed across various well-established datasets to demonstrate the advantages of the QABBA method for symbolic approximation.