LogoRA: Local-Global Representation Alignment for Robust Time Series Classification
Not on the map. Why?
Abstract (arXiv)
Unsupervised domain adaptation (UDA) of time series aims to teach models to identify consistent patterns across various temporal scenarios, disregarding domain-specific differences, which can maintain their predictive accuracy and effectively adapt to new domains. However, existing UDA methods struggle to adequately extract and align both global and local features in time series data. To address this issue, we propose the Local-Global Representation Alignment framework (LogoRA), which employs a two-branch encoder, comprising a multi-scale convolutional branch and a patching transformer branch. The encoder enables the extraction of both local and global representations from time series. A fusion module is then introduced to integrate these representations, enhancing domain-invariant feature alignment from multi-scale perspectives. To achieve effective alignment, LogoRA employs strategies like invariant feature learning on the source domain, utilizing triplet loss for fine alignment and dynamic time warping-based feature alignment. Additionally, it reduces source-target domain gaps through adversarial training and per-class prototype alignment. Our evaluations on four time-series datasets demonstrate that LogoRA outperforms strong baselines by up to 12.52%, showcasing its superiority in time series UDA tasks.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 35 of its 60 references that are in the map. First posted on arXiv 12 Sep 2024.
Builds on
35 of 60 references.
References · 35
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
- 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
- 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
- 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
- 2017Adversarial Discriminative Domain Adaptationcited by 1,309
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
- 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
- 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
- 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 308
- 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
- 2018Multi-Adversarial Domain Adaptationcited by 195
23 more
- 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
- 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
- 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
- 2016Multi-Scale Convolutional Neural Networks for Time Series Classificationcited by 99
- 2019HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptationcited by 89
- 2020Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Datacited by 82
- 2016Beyond Sharing Weights for Deep Domain Adaptationcited by 80
- 2022Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identificationcited by 78
- 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
- 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 71
- 2021Domain Adaptation for Time Series Forecasting via Attention Sharingcited by 68
- 2023Domain Adaptation for Time Series Under Feature and Label Shiftscited by 60
- 2021CLDA: Contrastive Learning for Semi-Supervised Domain Adaptationcited by 52
- 2020Time Series Domain Adaptation via Sparse Associative Structure Alignmentcited by 51
- 2023AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptationcited by 48
- 2019Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Valuescited by 37
- 2022Contrastive Learning for Unsupervised Domain Adaptation of Time Seriescited by 36
- 2020Gradient Regularized Contrastive Learning for Continual Domain Adaptationcited by 35
- 2019On Minimum Discrepancy Estimation for Deep Domain Adaptationcited by 34
- 2023Free Lunch for Domain Adversarial Training: Environment Label Smoothingcited by 33
- 2015A Smoothed Dual Approach for Variational Wasserstein Problemscited by 29
- 2022Domain-Specific Risk Minimization for Out-of-Distribution Generalizationcited by 15
- 2021When is Early Classification of Time Series Meaningful?cited by 9
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.