Learning Compositional Transferability of Time Series for Source-Free Domain Adaptation
Domain adaptation is challenging for time series classification due to the highly dynamic nature. This study tackles the most difficult subtask when both target labels and source data are inaccessible, namely, source-free domain adaptation. To reuse the classification backbone pre-trained on source data, time series reconstruction is a sound solution that aligns target and source time series by minimizing the reconstruction errors of both. However, simply fine-tuning the source pre-trained reconstruction model on target data may lose the learnt priori, and it struggles to accommodate domain varying temporal patterns in a single encoder-decoder. Therefore, this paper tries to disentangle the composition of domain transferability by using a compositional architecture for time series reconstruction. Here, the preceding component is a U-net frozen since pre-trained, the output of which during adaptation is the initial reconstruction of a given target time series, acting as a coarse step to prompt the subsequent finer adaptation. The following pipeline for finer adaptation includes two parallel branches: The source replay branch using a residual link to preserve the output of U-net, and the offset compensation branch that applies an additional autoencoder (AE) to further warp U-net's output. By deploying a learnable factor on either branch to scale their composition in the final output of reconstruction, the data transferability is disentangled and the learnt reconstructive capability from source data is retained. During inference, aside from the batch-level optimization in the training, we search at test time stability-aware rescaling of source replay branch to tolerate instance-wise variation. The experimental results show that such compositional architecture of time series reconstruction leads to SOTA performance on 3 widely used benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationSource-Free Domain AdaptationTime SeriesTime Series ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Compositionality in Time Series: A Proof of Concept using Symbolic Dynamics and Compositional Data Augmentation
This work investigates whether time series of natural phenomena can be understood as being generated by sequences of latent states which are ordered in systematic and regular ways. We focus on clinical time series and as…
Time Series ForecastingData AugmentationDomain AdaptationCompositional Zero-Shot Domain Transfer with Text-to-Text Models
Label scarcity is a bottleneck for improving task performance in specialised domains. We propose a novel compositional transfer learning framework (DoT5 - domain compositional zero-shot T5) for zero-shot domain transfer.…
Data AugmentationMulti-Task LearningTransfer LearningModel Selection with a Shapelet-based Distance Measure for Multi-source Transfer Learning in Time Series Classification
Transfer learning is a common practice that alleviates the need for extensive data to train neural networks. It is performed by pre-training a model using a source dataset and fine-tuning it for a target task. However, n…
Model SelectionTime SeriesTime Series ClassificationTransfer LearningTTOM: Test-Time Optimization and Memorization for Compositional Video Generation
Video Foundation Models (VFMs) exhibit remarkable visual generation performance, but struggle in compositional scenarios (e.g., motion, numeracy, and spatial relation). In this work, we introduce Test-Time Optimization a…
Video GenerationBeyond Forecasting: Compositional Time Series Reasoning for End-to-End Task Execution
In recent decades, there has been substantial advances in time series models and benchmarks across various individual tasks, such as time series forecasting, classification, and anomaly detection. Meanwhile, compositiona…
Anomaly DetectionDecision MakingLarge Language ModelQuestion Answering+2