paper-with-me

Papers

Learning Compositional Transferability of Time Series for Source-Free Domain Adaptation

2025-04-21 · Hankang Sun, Guiming Li, Su Yang, Baoqi Li

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.

📄 PDF Abstract BibTeX arXiv:2504.14994

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationSource-Free Domain AdaptationTime SeriesTime Series Classification

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

Compositionality in Time Series: A Proof of Concept using Symbolic Dynamics and Compositional Data Augmentation

2025-08-28 · Michael Hagmann, Michael Staniek, Stefan Riezler arxiv

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 Adaptation

Compositional Zero-Shot Domain Transfer with Text-to-Text Models

2023-03-23 · Fangyu Liu, Qianchu Liu, Shruthi Bannur, Fernando Pérez-García 외

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 Learning

Model Selection with a Shapelet-based Distance Measure for Multi-source Transfer Learning in Time Series Classification

2024-09-30 · Jiseok Lee, Brian Kenji Iwana

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 Learning

TTOM: Test-Time Optimization and Memorization for Compositional Video Generation

2025-10-09 · Leigang Qu, Ziyang Wang, Na Zheng, Wenjie Wang 외 arxiv

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 Generation

Beyond Forecasting: Compositional Time Series Reasoning for End-to-End Task Execution

2024-10-05 · Wen Ye, Yizhou Zhang, Wei Yang, Lumingyuan Tang 외

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