Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization

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.

Tensor-Ring Nuclear Norm Minimization and Application for Visual Data Completion

Tensor ring (TR) decomposition has been successfully used to obtain the state-of-the-art performance in the visual data completion problem. However, the existing TR-based completion methods are severely non-convex and computationally demanding. In addition, the determination of the optimal TR rank is a tough work in practice. To overcome these drawbacks, we first introduce a class of new tensor nuclear norms by using tensor circular unfolding. Then we theoretically establish connection between the rank of the circularly-unfolded matrices and the TR ranks. We also develop an efficient tensor completion algorithm by minimizing the proposed tensor nuclear norm. Extensive experimental results demonstrate that our proposed tensor completion method outperforms the conventional tensor completion methods in the image/video in-painting problem with striped missing values.

Tucker Tensor Layer in Fully Connected Neural Networks

We introduce the Tucker Tensor Layer (TTL), an alternative to the dense weight-matrices of the fully connected layers of feed-forward neural networks (NNs), to answer the long standing quest to compress NNs and improve their interpretability. This is achieved by treating these weight-matrices as the unfolding of a higher order weight-tensor. This enables us to introduce a framework for exploiting the multi-way nature of the weight-tensor in order to efficiently reduce the number of parameters, by virtue of the compression properties of tensor decompositions. The Tucker Decomposition (TKD) is employed to decompose the weight-tensor into a core tensor and factor matrices. We re-derive back-propagation within this framework, by extending the notion of matrix derivatives to tensors. In this way, the physical interpretability of the TKD is exploited to gain insights into training, through the process of computing gradients with respect to each factor matrix. The proposed framework is validated on synthetic data and on the Fashion-MNIST dataset, emphasizing the relative importance of various data features in training, hence mitigating the "black-box" issue inherent to NNs. Experiments on both MNIST and Fashion-MNIST illustrate the compression properties of the TTL, achieving a 66.63 fold compression whilst maintaining comparable performance to the uncompressed NN.

Randomized Tensor Ring Decomposition and Its Application to Large-scale Data Reconstruction

Dimensionality reduction is an essential technique for multi-way large-scale data, i.e., tensor. Tensor ring (TR) decomposition has become popular due to its high representation ability and flexibility. However, the traditional TR decomposition algorithms suffer from high computational cost when facing large-scale data. In this paper, taking advantages of the recently proposed tensor random projection method, we propose two TR decomposition algorithms. By employing random projection on every mode of the large-scale tensor, the TR decomposition can be processed at a much smaller scale. The simulation experiment shows that the proposed algorithms are $4-25$ times faster than traditional algorithms without loss of accuracy, and our algorithms show superior performance in deep learning dataset compression and hyperspectral image reconstruction experiments compared to other randomized algorithms.

Non-local Meets Global: An Integrated Paradigm for Hyperspectral Denoising

Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) denoising. Unfortunately, with more spectral bands for HSI, while the running time of these methods significantly increases, their denoising performance benefits little. In this paper, we claim that the HSI underlines a global spectral low-rank subspace, and the spectral subspaces of each full band patch groups should underlie this global low-rank subspace. This motivates us to propose a unified spatial-spectral paradigm for HSI denoising. As the new model is hard to optimize, we further propose an efficient algorithm for optimization, which is motivated by alternating minimization. This is done by first learning a low-dimensional projection and the related reduced image from the noisy HSI. Then, the non-local low-rank denoising and iterative regularization are developed to refine the reduced image and projection, respectively. Finally, experiments on synthetic and both real datasets demonstrate the superiority against the other state-of-the-arts HSI denoising methods.

AI Neurotechnology for Aging Societies -- Task-load and Dementia EEG Digital Biomarker Development Using Information Geometry Machine Learning Methods

Dementia and especially Alzheimer's disease (AD) are the most common causes of cognitive decline in elderly people. A spread of the above mentioned mental health problems in aging societies is causing a significant medical and economic burden in many countries around the world. According to a recent World Health Organization (WHO) report, it is approximated that currently, worldwide, about 47 million people live with a dementia spectrum of neurocognitive disorders. This number is expected to triple by 2050, which calls for possible application of AI-based technologies to support an early screening for preventive interventions and a subsequent mental wellbeing monitoring as well as maintenance with so-called digital-pharma or beyond a pill therapeutical approaches. This paper discusses our attempt and preliminary results of brainwave (EEG) techniques to develop digital biomarkers for dementia progress detection and monitoring. We present an information geometry-based classification approach for automatic EEG-derived event related responses (ERPs) discrimination of low versus high task-load auditory or tactile stimuli recognition, of which amplitude and latency variabilities are similar to those in dementia. The discussed approach is a step forward to develop AI, and especially machine learning (ML) approaches, for the subsequent application to mild-cognitive impairment (MCI) and AD diagnostics.

Low-Rank Embedding of Kernels in Convolutional Neural Networks under Random Shuffling

Although the convolutional neural networks (CNNs) have become popular for various image processing and computer vision task recently, it remains a challenging problem to reduce the storage cost of the parameters for resource-limited platforms. In the previous studies, tensor decomposition (TD) has achieved promising compression performance by embedding the kernel of a convolutional layer into a low-rank subspace. However the employment of TD is naively on the kernel or its specified variants. Unlike the conventional approaches, this paper shows that the kernel can be embedded into more general or even random low-rank subspaces. We demonstrate this by compressing the convolutional layers via randomly-shuffled tensor decomposition (RsTD) for a standard classification task using CIFAR-10. In addition, we analyze how the spatial similarity of the training data influences the low-rank structure of the kernels. The experimental results show that the CNN can be significantly compressed even if the kernels are randomly shuffled. Furthermore, the RsTD-based method yields more stable classification accuracy than the conventional TD-based methods in a large range of compression ratios.

Exact Recovery of Low-rank Tensor Decomposition under Reshuffling

Low-rank tensor decomposition is a promising approach for analysis and understanding of real-world data. Many such analyses require correct recovery of the true latent factors, but the conditions of exact recovery are not known for many existing tensor decomposition methods. In this paper, we derive such conditions for a general class of tensor decomposition methods where each latent tensor component can be reshuffled into a low-rank matrix of arbitrary shape. The reshuffling operation generalizes the traditional unfolding operation, and provides flexibility to recover true latent factors of complex data-structures. We prove that exact recovery can be guaranteed by using a convex program when a type of incoherence measure is upper bounded. The results on image steganography show that our method obtains the state-of-the-art performance. The theoretical analysis in this paper is expected to be useful to derive similar results for other types of tensor-decomposition methods.

Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion

In tensor completion tasks, the traditional low-rank tensor decomposition models suffer from laborious model selection problem due to high model sensitivity. Especially for tensor ring (TR) decomposition, the number of model possibility grows exponentially with the tensor order, which makes it rather challenging to find the optimal TR decomposition. In this paper, by exploiting the low-rank structure on TR latent space, we propose a novel tensor completion method, which is robust to model selection. In contrast to imposing low-rank constraint on the data space, we introduce nuclear norm regularization on the latent TR factors, resulting in that the optimization step using singular value decomposition (SVD) can be performed at a much smaller scale. By leveraging the alternating direction method of multipliers (ADMM) scheme, the latent TR factors with optimal rank and the recovered tensor can be obtained simultaneously. Our proposed algorithm effectively alleviates the burden of TR-rank selection, therefore the computational cost is greatly reduced. The extensive experimental results on synthetic data and real-world data demonstrate the superior high performance and efficiency of the proposed approach against the state-of-the-art algorithms.

Brain-Computer Interface with Corrupted EEG Data: A Tensor Completion Approach

One of the current issues in Brain-Computer Interface is how to deal with noisy Electroencephalography measurements organized as multidimensional datasets. On the other hand, recently, significant advances have been made in multidimensional signal completion algorithms that exploit tensor decomposition models to capture the intricate relationship among entries in a multidimensional signal. We propose to use tensor completion applied to EEG data for improving the classification performance in a motor imagery BCI system with corrupted measurements. Noisy measurements are considered as unknowns that are inferred from a tensor decomposition model. We evaluate the performance of four recently proposed tensor completion algorithms plus a simple interpolation strategy, first with random missing entries and then with missing samples constrained to have a specific structure (random missing channels), which is a more realistic assumption in BCI Applications. We measured the ability of these algorithms to reconstruct the tensor from observed data. Then, we tested the classification accuracy of imagined movement in a BCI experiment with missing samples. We show that for random missing entries, all tensor completion algorithms can recover missing samples increasing the classification performance compared to a simple interpolation approach. For the random missing channels case, we show that tensor completion algorithms help to reconstruct missing channels, significantly improving the accuracy in the classification of motor imagery, however, not at the same level as clean data. Tensor completion algorithms are useful in real BCI applications. The proposed strategy could allow using motor imagery BCI systems even when EEG data is highly affected by missing channels and/or samples, avoiding the need of new acquisitions in the calibration stage.