Arunan, A., Qin, Y., Li, X., & Yuen, C. (2025). Intelligently Augmented Contrastive Tensor Factorization: Empowering multi-dimensional time series classification in low-data environments. Expert Systems with Applications, 287, 127889. https://doi.org/10.1016/j.eswa.2025.127889
Abstract:
Classification of multi-dimensional time series from
real-world systems require fine-grained learning of complex
features such as cross-dimensional dependencies and intra-class
variations—all under the practical challenge of low training
data availability. However, standard deep learning (DL) struggles
to learn generalizable features in low-data environments
due to model overfitting. We propose a versatile yet dataefficient
framework, Intelligently Augmented Contrastive Tensor
Factorization (ITA-CTF), to learn effective representations from
multi-dimensional time series. The CTF module learns core
explanatory components of the time series (e.g., sensor factors,
temporal factors), and importantly, their joint dependencies.
Notably, unlike standard tensor factorization (TF), the CTF
module incorporates a new contrastive loss optimization to induce
similarity learning and class-awareness into the learnt representations
for better classification performance. To strengthen
this contrastive learning, the preceding ITA module generates
targeted but informative augmentations that highlight realistic
intra-class patterns in the original data, while preserving classwise
properties. This is achieved by dynamically sampling a
“soft” class prototype to guide the warping of each query data
sample, which results in an augmentation that is intelligently
pattern-mixed between the “soft” class prototype and the query
sample. These augmentations enable the CTF module to recognize
complex intra-class variations despite the limited original
training data, and seek out invariant class-wise properties for
accurate classification performance. The proposed method is
comprehensively evaluated on five different classification tasks,
including extremely challenging tasks such as fault localization
with more than 50 classes. Compared to standard TF and several
DL benchmarks, notable performance improvements up to 18.7%
were achieved.
License type:
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Funding Info:
There was no specific funding for the research done