Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LAMPER: LanguAge Model and Prompt EngineeRing for zero-shot time series classification

Zhicheng Du, Zhaotian Xie, Yan Tong, Peiwu Qin

TL;DR

Findings indicate that the feature representation capacity of LAMPER is influenced by the maximum input token threshold imposed by PLMs, which is influenced by the maximum input token threshold imposed by PLMs.

Abstract

This study constructs the LanguAge Model with Prompt EngineeRing (LAMPER) framework, designed to systematically evaluate the adaptability of pre-trained language models (PLMs) in accommodating diverse prompts and their integration in zero-shot time series (TS) classification. We deploy LAMPER in experimental assessments using 128 univariate TS datasets sourced from the UCR archive. Our findings indicate that the feature representation capacity of LAMPER is influenced by the maximum input token threshold imposed by PLMs.

LAMPER: LanguAge Model and Prompt EngineeRing for zero-shot time series classification

TL;DR

Findings indicate that the feature representation capacity of LAMPER is influenced by the maximum input token threshold imposed by PLMs, which is influenced by the maximum input token threshold imposed by PLMs.

Abstract

This study constructs the LanguAge Model with Prompt EngineeRing (LAMPER) framework, designed to systematically evaluate the adaptability of pre-trained language models (PLMs) in accommodating diverse prompts and their integration in zero-shot time series (TS) classification. We deploy LAMPER in experimental assessments using 128 univariate TS datasets sourced from the UCR archive. Our findings indicate that the feature representation capacity of LAMPER is influenced by the maximum input token threshold imposed by PLMs.
Paper Structure (8 sections, 2 figures, 3 tables)

This paper contains 8 sections, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Experiments
  4. Discussion and Conclusion
  5. Prompts' format
  6. CD diagram of LAMPER with SVM
  7. Ablation experiment
  8. 128 univariate datasets of UCR archive and experimental results

Figures (2)

  • Figure 1: Overall pipeline of LAMPER for zero-shot time series classification.
  • Figure 2: CD diagram of LAMPER with SVM on zero-shot time series classification tasks with a confidence level of 95%, where classifiers that are not connected by a bold line are significantly different in average ranks.