# Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization

## TL;DR

This paper introduces a tensor rank regularization method to improve multimodal time series data representations, effectively handling noise and missing data by leveraging low-rank structures.

## Contribution

The paper proposes a novel tensor rank minimization regularization technique specifically designed for imperfect multimodal time series data.

## Key findings

- Model achieves robust performance across various levels of data imperfection.
- Effective regularization reduces tensor rank, capturing correlations in multimodal data.
- Improves representation quality in noisy and incomplete multimodal datasets.

## Abstract

There has been an increased interest in multimodal language processing including multimodal dialog, question answering, sentiment analysis, and speech recognition. However, naturally occurring multimodal data is often imperfect as a result of imperfect modalities, missing entries or noise corruption. To address these concerns, we present a regularization method based on tensor rank minimization. Our method is based on the observation that high-dimensional multimodal time series data often exhibit correlations across time and modalities which leads to low-rank tensor representations. However, the presence of noise or incomplete values breaks these correlations and results in tensor representations of higher rank. We design a model to learn such tensor representations and effectively regularize their rank. Experiments on multimodal language data show that our model achieves good results across various levels of imperfection.