Timezone: »

ATD: Augmenting CP Tensor Decomposition by Self Supervision
Chaoqi Yang · Cheng Qian · Navjot Singh · Cao (Danica) Xiao · M Westover · Edgar Solomonik · Jimeng Sun

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #422

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 tensor 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.

Author Information

Chaoqi Yang (University of Illinois Urbana Champaign)
Cheng Qian (IQVIA)
Navjot Singh (University of Illinois, Urbana Champaign)
Cao (Danica) Xiao (Relativity)
M Westover (Massachusetts General Hospital, Harvard University)
Edgar Solomonik (University of Illinois, Urbana Champaign)
Jimeng Sun (University of Illinois, Urbana Champaign)

More from the Same Authors