Timezone: »

 
Poster
Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency
Xiang Zhang · Ziyuan Zhao · Theodoros Tsiligkaridis · Marinka Zitnik

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #204
in Poster Session 2 »

Pre-training on time series poses a unique challenge due to the potential mismatch between pre-training and target domains, such as shifts in temporal dynamics, fast-evolving trends, and long-range and short-cyclic effects, which can lead to poor downstream performance. While domain adaptation methods can mitigate these shifts, most methods need examples directly from the target domain, making them suboptimal for pre-training. To address this challenge, methods need to accommodate target domains with different temporal dynamics and be capable of doing so without seeing any target examples during pre-training. Relative to other modalities, in time series, we expect that time-based and frequency-based representations of the same example are located close together in the time-frequency space. To this end, we posit that time-frequency consistency (TF-C) --- embedding a time-based neighborhood of an example close to its frequency-based neighborhood --- is desirable for pre-training. Motivated by TF-C, we define a decomposable pre-training model, where the self-supervised signal is provided by the distance between time and frequency components, each individually trained by contrastive estimation. We evaluate the new method on eight datasets, including electrodiagnostic testing, human activity recognition, mechanical fault detection, and physical status monitoring. Experiments against eight state-of-the-art methods show that TF-C outperforms baselines by 15.4% (F1 score) on average in one-to-one settings (e.g., fine-tuning an EEG-pretrained model on EMG data) and by 8.4% (precision) in challenging one-to-many settings (e.g., fine-tuning an EEG-pretrained model for either hand-gesture recognition or mechanical fault prediction), reflecting the breadth of scenarios that arise in real-world applications. The source code and datasets are available at https://github.com/mims-harvard/TFC-pretraining.

Keywords: Self-supervised learning · time series · transfer learning · contrastive learning · pre-training
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Xiang Zhang (University of North Carolina at Charlotte)

Xiang is an Assistant Professor in the Department of Computer Science at the University of North Carolina (UNC) at Charlotte. Before joining UNC Charlotte, he was a postdoctoral fellow at Harvard University. Machine learning, data mining, graph neural networks, medical time series, EEG

Ziyuan Zhao (Harvard University)
Theodoros Tsiligkaridis (MIT Lincoln Laboratory)
Marinka Zitnik (Harvard University)

More from the Same Authors