Data Augmentation in Time Series Forecasting through Inverted Framework

2025/07/15 by Hongming Tan, Tan, Hongming, Ting Chen +4
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2507.11439

openalex publication_date 2025/07/15 · openalex created_date 2025/10/09 · openalex updated_date 2026/07/28

Abstract

Currently, iTransformer is one of the most popular and effective models for multivariate time series (MTS) forecasting. Thanks to its inverted framework, iTransformer effectively captures multivariate correlation. However, the inverted framework still has some limitations. It diminishes temporal interdependency information, and introduces noise in cases of nonsignificant variable correlation. To address these limitations, we introduce a novel data augmentation method on inverted framework, called DAIF. Unlike previous data augmentation methods, DAIF stands out as the first real-time augmentation specifically designed for the inverted framework in MTS forecasting. We first define the structure of the inverted sequence-to-sequence framework, then propose two different DAIF strategies, Frequency Filtering and Cross-variation Patching to address the existing challenges of the inverted framework. Experiments across multiple datasets and inverted models have demonstrated the effectiveness of our DAIF.

Citations

• Deep Time Series Models: A Comprehensive Survey and Benchmark
• TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
• TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting
• TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
• iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
• Are Transformers Effective for Time Series Forecasting?
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Improving the Accuracy of Global Forecasting Models using Time Series\n Data Augmentation
• RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks
• Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
• Attention Is All You Need
• DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
• Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Surrogate time series
• Long Short-Term Memory
• Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping

Related

• InvDec: Inverted Decoder for Multivariate Time Series Forecasting with Separated Temporal and Variate Modeling
• Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling
• Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift
• iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
• TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster