ATD: Augmenting CP Tensor Decomposition by Self Supervision

arXiv2106.07900MaRDI QIDQ6370331FDOQ6370331

Jimeng Sun, Chaoqi Yang, Edgar Solomonik, Cheng Qian, M. Brandon Westover, Cao Xiao, Navjot Singh

Publication date: 15 June 2021

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

Has companion code repository: https://github.com/ycq091044/atd

This page was built for publication: ATD: Augmenting CP Tensor Decomposition by Self Supervision

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6370331)