Intelligently Augmented Contrastive Tensor Factorization: Empowering Multi-dimensional Time Series Classification in Low-Data Environments

2025-05-03

AI Summary

Few-shot multidimensional time series classification suffers from challenges in modeling cross-dimensional dependencies and large intra-class variability, leading to severe overfitting in deep models. Method: This paper proposes an intelligent augmentation-enhanced contrastive tensor decomposition framework. First, it introduces a novel contrastive loss-driven tensor decomposition module that jointly disentangles multi-dimensional factors (e.g., sensors, time) and their high-order interactions. Second, it designs a soft class-prototype-guided dynamic time warping (DTW) augmentation mechanism to enable class-aware representation learning and temporal invariance. Results: Evaluated on five low-data regimes, the method achieves up to 18.7% absolute accuracy improvement over standard tensor decomposition and deep learning baselines, demonstrating significantly enhanced model robustness and generalization capability.

Technology Category

• Machine Learning: Matrix & Tensor Methods
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

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 data-efficient 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 class-wise 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. Compared to standard TF and several DL benchmarks, notable performance improvements up to 18.7% were achieved.

Problem

• Classify multi-dimensional time series with limited training data
• Learn cross-dimensional dependencies and intra-class variations effectively
• Prevent model overfitting in low-data environments

Innovation

• Contrastive Tensor Factorization for dependency learning
• Intelligently Targeted Augmentation for data enrichment
• Dynamic soft class prototype for pattern mixing