TSVer is a new benchmark dataset for fact verification against time-series evidence, with 304 annotated real-world claims, 400 time series, verdicts, and justifications, plus baseline results showing current models struggle.
hub
One fits all: Power general time series analysis by pretrained lm
10 Pith papers cite this work, alongside 118 external citations. Polarity classification is still indexing.
10
Pith papers citing it
118
external citations · Pith
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.
hub tools
citation-role summary
contradiction 1
citation-polarity summary
roles
contradiction 1polarities
contest 1representative citing papers
A pretrained decoder-only patched transformer achieves near state-of-the-art zero-shot forecasting performance across diverse time series datasets and settings.
Compares foundation models for probabilistic low-voltage load forecasting on 200 real feeders and introduces a grid-planning metric that scores peak prediction by its effect on asset cost-risk decisions.
ADAPT is a new pre-training paradigm that aligns physical properties of time-series data to allow simultaneous training on 162 diverse classification datasets, achieving new state-of-the-art performance.
Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.
A frozen LLM plus a pretrained trajectory encoder, joined by a small adapter, predicts remaining terminal-area time with ~0.92-minute MAE on Incheon 2022 data.
TSF converts process variable documents into frozen semantic vectors that scale the numerical input window before a time-series backbone, yielding average MAE reductions of 2.9–3.6% across industrial forecasting tasks.
MSTN claims SOTA across time-series tasks with early temporal pooling, but internal inconsistencies in parameter counts, benchmark tables, and implausible error reductions undermine the central claims.
Pre-training a transformer on the TSX index reduces binary cross-entropy loss on individual stocks from 0.69 to 0.64 and yields lower MSE than LSTM or XGBoost in regression, though ensembles achieve higher average daily returns.
A survey that proposes a taxonomy for universal time-series representation learning and reviews existing deep learning studies along with experimental setups.
citing papers explorer
-
TSVer: A Benchmark for Fact Verification Against Time-Series Evidence
TSVer is a new benchmark dataset for fact verification against time-series evidence, with 304 annotated real-world claims, 400 time series, verdicts, and justifications, plus baseline results showing current models struggle.
-
A decoder-only foundation model for time-series forecasting
A pretrained decoder-only patched transformer achieves near state-of-the-art zero-shot forecasting performance across diverse time series datasets and settings.
-
Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics
Compares foundation models for probabilistic low-voltage load forecasting on 200 real feeders and introduces a grid-planning metric that scores peak prediction by its effect on asset cost-risk decisions.
-
ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification
ADAPT is a new pre-training paradigm that aligns physical properties of time-series data to allow simultaneous training on 162 diverse classification datasets, achieving new state-of-the-art performance.
-
Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.
-
LLM4Delay: Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation
A frozen LLM plus a pretrained trajectory encoder, joined by a small adapter, predicts remaining terminal-area time with ~0.92-minute MAE on Incheon 2022 data.
-
LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting
TSF converts process variable documents into frozen semantic vectors that scale the numerical input window before a time-series backbone, yielding average MAE reductions of 2.9–3.6% across industrial forecasting tasks.
-
MSTN: A Lightweight and Fast Model for General TimeSeries Analysis
MSTN claims SOTA across time-series tasks with early temporal pooling, but internal inconsistencies in parameter counts, benchmark tables, and implausible error reductions undermine the central claims.
-
From Index to Equity: Pre-Training Transformers for Stock Return Prediction
Pre-training a transformer on the TSX index reduces binary cross-entropy loss on individual stocks from 0.69 to 0.64 and yields lower MSE than LSTM or XGBoost in regression, though ensembles achieve higher average daily returns.
-
Universal Time-Series Representation Learning: A Survey
A survey that proposes a taxonomy for universal time-series representation learning and reviews existing deep learning studies along with experimental setups.