ATD: Augmenting CP Tensor Decomposition by Self Supervision

TL;DR

This paper introduces ATD, a novel tensor decomposition method that integrates data augmentation and self-supervised learning to improve classification accuracy on multidimensional data.

Contribution

It proposes a new augmented tensor decomposition framework that incorporates data augmentation and SSL, optimized via an ALS-like iterative method, enhancing downstream classification performance.

Findings

Achieves 0.8%-2.5% accuracy improvement over tensor baselines.

Outperforms self-supervised and autoencoder models by up to 15% in accuracy.

Uses less than 5% of the parameters compared to baseline models.

Abstract

Tensor decompositions are powerful tools for dimensionality reduction and feature interpretation of multidimensional data such as signals. Existing tensor decomposition objectives (e.g., Frobenius norm) are designed for fitting raw data under statistical assumptions, which may not align with downstream classification tasks. In practice, raw input tensors can contain irrelevant information while data augmentation techniques may be used to smooth out class-irrelevant noise in samples. This paper addresses the above challenges by proposing augmented tensor decomposition (ATD), which effectively incorporates data augmentations and self-supervised learning (SSL) to boost downstream classification. To address the non-convexity of the new augmented objective, we develop an iterative method that enables the optimization to follow an alternating least squares (ALS) fashion. We evaluate our proposed ATD on multiple datasets. It can achieve 0.8% - 2.5% accuracy gain over tensor-based baselines. Also, our ATD model shows comparable or better performance (e.g., up to 15% in accuracy) over self-supervised and autoencoder baselines while using less than 5% of learnable parameters of these baseline models