{"work":{"id":"e1410b9b-bc47-4f1f-9aee-a4821fcfa504","openalex_id":"https://openalex.org/W4321854470","doi":"10.48550/arxiv.2302.11939","arxiv_id":"2302.11939","raw_key":null,"title":"One Fits All:Power General Time Series Analysis by Pretrained LM","authors":null,"authors_text":"One Fits All: Power General Time Series Analysis by Pretrained LM , author=","year":2023,"venue":"cs.LG","abstract":"Although we have witnessed great success of pre-trained models in natural language processing (NLP) and computer vision (CV), limited progress has been made for general time series analysis. Unlike NLP and CV where a unified model can be used to perform different tasks, specially designed approach still dominates in each time series analysis task such as classification, anomaly detection, forecasting, and few-shot learning. The main challenge that blocks the development of pre-trained model for time series analysis is the lack of a large amount of data for training. In this work, we address this challenge by leveraging language or CV models, pre-trained from billions of tokens, for time series analysis. Specifically, we refrain from altering the self-attention and feedforward layers of the residual blocks in the pre-trained language or image model. This model, known as the Frozen Pretrained Transformer (FPT), is evaluated through fine-tuning on all major types of tasks involving time series. Our results demonstrate that pre-trained models on natural language or images can lead to a comparable or state-of-the-art performance in all main time series analysis tasks, as illustrated in Figure 1. We also found both theoretically and empirically that the self-attention module behaviors similarly to principle component analysis (PCA), an observation that helps explains how transformer bridges the domain gap and a crucial step towards understanding the universality of a pre-trained transformer.The code is publicly available at https://github.com/DAMO-DI-ML/One_Fits_All.","external_url":"https://arxiv.org/abs/2302.11939","cited_by_count":118,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2302.11939","created_at":"2026-05-11T07:25:59.991698+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"One fits all: Power general time series analysis by pretrained lm","render_title":"One fits all: Power general time series analysis by pretrained lm"},"hub":{"state":{"tier_text":"hub","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":10,"external_cited_by_count":118},"tier":"hub","role_counts":[{"context_role":"contradiction","n":1}],"polarity_counts":[{"context_polarity":"contest","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}