PyTorchKR Papers

최신 논문

총 579편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2207.02851

Tensor networks in machine learning

A tensor network is a type of decomposition used to express and approximate large arrays of data. A given data-set, quantum state or higher dimensional multi-linear map is factored and approximated by a composition of smaller multi-linear maps. This is reminiscent to how a Boolean function might be decomposed into a gate array: this represents a special case of tensor decomposition, in which the tensor entries are replaced by 0, 1 and the factorisation becomes exact. The collection of associated techniques are called, tensor network methods: the subject developed independently in several distinct fields of study, which have more recently become interrelated through the language of tensor networks. The tantamount questions in the field relate to expressability of tensor networks and the reduction of computational overheads. A merger of tensor networks with machine learning is natural. On the one hand, machine learning can aid in determining a factorization of a tensor network approximating a data set. On the other hand, a given tensor network structure can be viewed as a machine learning model. Herein the tensor network parameters are adjusted to learn or classify a data-set. In this survey we recover the basics of tensor networks and explain the ongoing effort to develop the theory of tensor networks in machine learning.

arXiv:2207.02446

Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition

Tensor decomposition is a fundamental framework to analyze data that can be represented by multi-dimensional arrays. In practice, tensor data is often accompanied by temporal information, namely the time points when the entry values were generated. This information implies abundant, complex temporal variation patterns. However, current methods always assume the factor representations of the entities in each tensor mode are static, and never consider their temporal evolution. To fill this gap, we propose NONparametric FActor Trajectory learning for dynamic tensor decomposition (NONFAT). We place Gaussian process (GP) priors in the frequency domain and conduct inverse Fourier transform via Gauss-Laguerre quadrature to sample the trajectory functions. In this way, we can overcome data sparsity and obtain robust trajectory estimates across long time horizons. Given the trajectory values at specific time points, we use a second-level GP to sample the entry values and to capture the temporal relationship between the entities. For efficient and scalable inference, we leverage the matrix Gaussian structure in the model, introduce a matrix Gaussian posterior, and develop a nested sparse variational learning algorithm. We have shown the advantage of our method in several real-world applications.

arXiv:2206.13355

A Simple and Scalable Tensor Completion Algorithm via Latent Invariant Constraint for Recommendation System

In this paper we provide a latent-variable formulation and solution to the recommender system (RS) problem in terms of a fundamental property that any reasonable solution should be expected to satisfy. Specifically, we examine a novel tensor completion method to efficiently and accurately learn parameters of a model for the unobservable personal preferences that underly user ratings. By regularizing the tensor decomposition with a single latent invariant, we achieve three properties for a reliable recommender system: (1) uniqueness of the tensor completion result with minimal assumptions, (2) unit consistency that is independent of arbitrary preferences of users, and (3) a consensus ordering guarantee that provides consistent ranking between observed and unobserved rating scores. Our algorithm leads to a simple and elegant recommendation framework that has linear computational complexity and with no hyperparameter tuning. We provide empirical results demonstrating that the approach significantly outperforms current state-of-the-art methods.

arXiv:2206.05427

Reconfigurable Intelligent Surface-Aided 6G Massive Access: Coupled Tensor Modeling and Sparse Bayesian Learning

This paper investigates a reconfigurable intelligent surface (RIS)-aided unsourced random access (URA) scheme for the sixth-generation (6G) wireless networks with massive sporadic traffic devices. First of all, this paper proposes a novel joint active device separation (the message recovery of active device) and channel estimation architecture for the RIS-aided URA. Specifically, the RIS passive reflection is optimized before the successful device separation. Then, by associating the data sequences to multiple rank-one tensors and exploiting the angular sparsity of the RIS-BS channel, the detection problem is cast as a high-order coupled tensor decomposition problem without the need of exploiting pilot sequences. However, the inherent coupling among multiple sparse device-RIS channels, together with the unknown number of active devices make the detection problem at hand deviate from the widely-used coupled tensor decomposition format. To overcome this challenge, this paper judiciously devises a probabilistic model that captures both the element-wise sparsity from the angular channel model and the low-rank property due to the sporadic nature of URA. Then, based on such a probabilistic model, a iterative detection algorithm is developed under the framework of sparse variational inference, where each update iteration is obtained in a closed-form and the number of active devices can be automatically estimated for effectively avoiding the overfitting of noise. Extensive simulation results confirm the excellence of the proposed URA algorithm, especially for the case of a large number of reflecting elements for accommodating a significantly large number of devices.

arXiv:2206.05341

Reducing the Control Overhead of Intelligent Reconfigurable Surfaces Via a Tensor-Based Low-Rank Factorization Approach

Passive intelligent reconfigurable surfaces (IRS) are becoming an attractive component of cellular networks due to their ability of shaping the propagation environment and thereby improving the coverage. While passive IRS nodes incorporate a great number of phase-shifting elements and a controller entity, the phase-shifts are typically determined by the cellular base station (BS) due to its computational capability. Since the fine granularity control of the large number of phase-shifters may become prohibitive in practice, it is important to reduce the control overhead between the BS and the IRS controller. To this end, in this paper we propose a low-rank approximation of the near-optimal phase-shifts, which would incur prohibitively high communication overhead on the BS-IRS controller links. The key idea is to represent the potentially large IRS phase-shift vector using a low-rank tensor model. This is achieved by factorizing a tensorized version of the IRS phase-shift vector, where each component is modeled as the Kronecker product of a predefined number of factors of smaller sizes, which can be obtained via tensor decomposition algorithms. We show that the proposed low-rank models drastically reduce the required feedback requirements associated with the BS-IRS control links. Our simulation results indicate that the proposed method is especially attractive in scenarios with a strong line of sight component, in which case nearly the same spectral efficiency is reached as in the cases with near-optimal phase-shifts, but with a drastically reduced communication overhead.

arXiv:2206.05651공식 코드 · Papers with Code

STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor Decomposition

Recent studies shows that the majority of existing deep steganalysis models have a large amount of redundancy, which leads to a huge waste of storage and computing resources. The existing model compression method cannot flexibly compress the convolutional layer in residual shortcut block so that a satisfactory shrinking rate cannot be obtained. In this paper, we propose STD-NET, an unsupervised deep-learning architecture search approach via hierarchical tensor decomposition for image steganalysis. Our proposed strategy will not be restricted by various residual connections, since this strategy does not change the number of input and output channels of the convolution block. We propose a normalized distortion threshold to evaluate the sensitivity of each involved convolutional layer of the base model to guide STD-NET to compress target network in an efficient and unsupervised approach, and obtain two network structures of different shapes with low computation cost and similar performance compared with the original one. Extensive experiments have confirmed that, on one hand, our model can achieve comparable or even better detection performance in various steganalytic scenarios due to the great adaptivity of the obtained network architecture. On the other hand, the experimental results also demonstrate that our proposed strategy is more efficient and can remove more redundancy compared with previous steganalytic network compression methods.

arXiv:2206.01509공식 코드 · Papers with Code

Canonical convolutional neural networks

We introduce canonical weight normalization for convolutional neural networks. Inspired by the canonical tensor decomposition, we express the weight tensors in so-called canonical networks as scaled sums of outer vector products. In particular, we train network weights in the decomposed form, where scale weights are optimized separately for each mode. Additionally, similarly to weight normalization, we include a global scaling parameter. We study the initialization of the canonical form by running the power method and by drawing randomly from Gaussian or uniform distributions. Our results indicate that we can replace the power method with cheaper initializations drawn from standard distributions. The canonical re-parametrization leads to competitive normalization performance on the MNIST, CIFAR10, and SVHN data sets. Moreover, the formulation simplifies network compression. Once training has converged, the canonical form allows convenient model-compression by truncating the parameter sums.

arXiv:2206.00850

Dynamic MRI using Learned Transform-based Tensor Low-Rank Network (LT$^2$LR-Net)

While low-rank matrix prior has been exploited in dynamic MR image reconstruction and has obtained satisfying performance, tensor low-rank models have recently emerged as powerful alternative representations for three-dimensional dynamic MR datasets. In this paper, we introduce a novel deep unrolling network for dynamic MRI, namely the learned transform-based tensor low-rank network (LT$^2$LR-Net). First, we generalize the tensor singular value decomposition (t-SVD) into an arbitrary unitary transform-based version and subsequently propose the novel transformed tensor nuclear norm (TTNN). Then, we design a novel TTNN-based iterative optimization algorithm based on the alternating direction method of multipliers (ADMM) to exploit the tensor low-rank prior in the transformed domain. The corresponding iterative steps are unrolled into the proposed LT$^2$LR-Net, where the convolutional neural network (CNN) is incorporated to adaptively learn the transformation from the dynamic MR dataset for more robust and accurate tensor low-rank representations. Experimental results on the cardiac cine MR dataset demonstrate that the proposed framework can provide improved recovery results compared with the state-of-the-art methods.

arXiv:2206.00635

Speech Artifact Removal from EEG Recordings of Spoken Word Production with Tensor Decomposition

Research about brain activities involving spoken word production is considerably underdeveloped because of the undiscovered characteristics of speech artifacts, which contaminate electroencephalogram (EEG) signals and prevent the inspection of the underlying cognitive processes. To fuel further EEG research with speech production, a method using three-mode tensor decomposition (time x space x frequency) is proposed to perform speech artifact removal. Tensor decomposition enables simultaneous inspection of multiple modes, which suits the multi-way nature of EEG data. In a picture-naming task, we collected raw data with speech artifacts by placing two electrodes near the mouth to record lip EMG. Based on our evaluation, which calculated the correlation values between grand-averaged speech artifacts and the lip EMG, tensor decomposition outperformed the former methods that were based on independent component analysis (ICA) and blind source separation (BSS), both in detecting speech artifact (0.985) and producing clean data (0.101). Our proposed method correctly preserved the components unrelated to speech, which was validated by computing the correlation value between the grand-averaged raw data without EOG and cleaned data before the speech onset (0.92-0.94).

arXiv:2205.15307공식 코드 · Papers with Code

A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks

Tensorial Convolutional Neural Networks (TCNNs) have attracted much research attention for their power in reducing model parameters or enhancing the generalization ability. However, exploration of TCNNs is hindered even from weight initialization methods. To be specific, general initialization methods, such as Xavier or Kaiming initialization, usually fail to generate appropriate weights for TCNNs. Meanwhile, although there are ad-hoc approaches for specific architectures (e.g., Tensor Ring Nets), they are not applicable to TCNNs with other tensor decomposition methods (e.g., CP or Tucker decomposition). To address this problem, we propose a universal weight initialization paradigm, which generalizes Xavier and Kaiming methods and can be widely applicable to arbitrary TCNNs. Specifically, we first present the Reproducing Transformation to convert the backward process in TCNNs to an equivalent convolution process. Then, based on the convolution operators in the forward and backward processes, we build a unified paradigm to control the variance of features and gradients in TCNNs. Thus, we can derive fan-in and fan-out initialization for various TCNNs. We demonstrate that our paradigm can stabilize the training of TCNNs, leading to faster convergence and better results.

arXiv:2205.14283

Rethinking Bayesian Learning for Data Analysis: The Art of Prior and Inference in Sparsity-Aware Modeling

Sparse modeling for signal processing and machine learning has been at the focus of scientific research for over two decades. Among others, supervised sparsity-aware learning comprises two major paths paved by: a) discriminative methods and b) generative methods. The latter, more widely known as Bayesian methods, enable uncertainty evaluation w.r.t. the performed predictions. Furthermore, they can better exploit related prior information and naturally introduce robustness into the model, due to their unique capacity to marginalize out uncertainties related to the parameter estimates. Moreover, hyper-parameters associated with the adopted priors can be learnt via the training data. To implement sparsity-aware learning, the crucial point lies in the choice of the function regularizer for discriminative methods and the choice of the prior distribution for Bayesian learning. Over the last decade or so, due to the intense research on deep learning, emphasis has been put on discriminative techniques. However, a come back of Bayesian methods is taking place that sheds new light on the design of deep neural networks, which also establish firm links with Bayesian models and inspire new paths for unsupervised learning, such as Bayesian tensor decomposition. The goal of this article is two-fold. First, to review, in a unified way, some recent advances in incorporating sparsity-promoting priors into three highly popular data modeling tools, namely deep neural networks, Gaussian processes, and tensor decomposition. Second, to review their associated inference techniques from different aspects, including: evidence maximization via optimization and variational inference methods. Challenges such as small data dilemma, automatic model structure search, and natural prediction uncertainty evaluation are also discussed. Typical signal processing and machine learning tasks are demonstrated.

arXiv:2205.15198

STN: Scalable Tensorizing Networks via Structure-Aware Training and Adaptive Compression

Deep neural networks (DNNs) have delivered a remarkable performance in many tasks of computer vision. However, over-parameterized representations of popular architectures dramatically increase their computational complexity and storage costs, and hinder their availability in edge devices with constrained resources. Regardless of many tensor decomposition (TD) methods that have been well-studied for compressing DNNs to learn compact representations, they suffer from non-negligible performance degradation in practice. In this paper, we propose Scalable Tensorizing Networks (STN), which dynamically and adaptively adjust the model size and decomposition structure without retraining. First, we account for compression during training by adding a low-rank regularizer to guarantee networks' desired low-rank characteristics in full tensor format. Then, considering network layers exhibit various low-rank structures, STN is obtained by a data-driven adaptive TD approach, for which the topological structure of decomposition per layer is learned from the pre-trained model, and the ranks are selected appropriately under specified storage constraints. As a result, STN is compatible with arbitrary network architectures and achieves higher compression performance and flexibility over other tensorizing versions. Comprehensive experiments on several popular architectures and benchmarks substantiate the superiority of our model towards improving parameter efficiency.

arXiv:2205.13163

Cost-efficient Gaussian Tensor Network Embeddings for Tensor-structured Inputs

This work discusses tensor network embeddings, which are random matrices ($S$) with tensor network structure. These embeddings have been used to perform dimensionality reduction of tensor network structured inputs $x$ and accelerate applications such as tensor decomposition and kernel regression. Existing works have designed embeddings for inputs $x$ with specific structures, such that the computational cost for calculating $Sx$ is efficient. We provide a systematic way to design tensor network embeddings consisting of Gaussian random tensors, such that for inputs with more general tensor network structures, both the sketch size (row size of $S$) and the sketching computational cost are low. We analyze general tensor network embeddings that can be reduced to a sequence of sketching matrices. We provide a sufficient condition to quantify the accuracy of such embeddings and derive sketching asymptotic cost lower bounds using embeddings that satisfy this condition and have a sketch size lower than any input dimension. We then provide an algorithm to efficiently sketch input data using such embeddings. The sketch size of the embedding used in the algorithm has a linear dependence on the number of sketching dimensions of the input. Assuming tensor contractions are performed with classical dense matrix multiplication algorithms, this algorithm achieves asymptotic cost within a factor of $O(\sqrt{m})$ of our cost lower bound, where $m$ is the sketch size. Further, when each tensor in the input has a dimension that needs to be sketched, this algorithm yields the optimal sketching asymptotic cost. We apply our sketching analysis to inexact tensor decomposition optimization algorithms. We provide a sketching algorithm for CP decomposition that is asymptotically faster than existing work in multiple regimes, and show optimality of an existing algorithm for tensor train rounding.

arXiv:2205.11691

High-Order Pooling for Graph Neural Networks with Tensor Decomposition

Graph Neural Networks (GNNs) are attracting growing attention due to their effectiveness and flexibility in modeling a variety of graph-structured data. Exiting GNN architectures usually adopt simple pooling operations (eg. sum, average, max) when aggregating messages from a local neighborhood for updating node representation or pooling node representations from the entire graph to compute the graph representation. Though simple and effective, these linear operations do not model high-order non-linear interactions among nodes. We propose the Tensorized Graph Neural Network (tGNN), a highly expressive GNN architecture relying on tensor decomposition to model high-order non-linear node interactions. tGNN leverages the symmetric CP decomposition to efficiently parameterize permutation-invariant multilinear maps for modeling node interactions. Theoretical and empirical analysis on both node and graph classification tasks show the superiority of tGNN over competitive baselines. In particular, tGNN achieves the most solid results on two OGB node classification datasets and one OGB graph classification dataset.

arXiv:2205.11153

Decoupling multivariate functions using a nonparametric filtered tensor decomposition

Multivariate functions emerge naturally in a wide variety of data-driven models. Popular choices are expressions in the form of basis expansions or neural networks. While highly effective, the resulting functions tend to be hard to interpret, in part because of the large number of required parameters. Decoupling techniques aim at providing an alternative representation of the nonlinearity. The so-called decoupled form is often a more efficient parameterisation of the relationship while being highly structured, favouring interpretability. In this work two new algorithms, based on filtered tensor decompositions of first order derivative information are introduced. The method returns nonparametric estimates of smooth decoupled functions. Direct applications are found in, i.a. the fields of nonlinear system identification and machine learning.

arXiv:2205.10651

Tensor Shape Search for Optimum Data Compression

Various tensor decomposition methods have been proposed for data compression. In real world applications of the tensor decomposition, selecting the tensor shape for the given data poses a challenge and the shape of the tensor may affect the error and the compression ratio. In this work, we study the effect of the tensor shape on the tensor decomposition and propose an optimization model to find an optimum shape for the tensor train (TT) decomposition. The proposed optimization model maximizes the compression ratio of the TT decomposition given an error bound. We implement a genetic algorithm (GA) linked with the TT-SVD algorithm to solve the optimization model. We apply the proposed method for the compression of RGB images. The results demonstrate the effectiveness of the proposed evolutionary tensor shape search for the TT decomposition.

arXiv:2205.10036공식 코드 · Papers with Code

Exploring Extreme Parameter Compression for Pre-trained Language Models

Recent work explored the potential of large-scale Transformer-based pre-trained models, especially Pre-trained Language Models (PLMs) in natural language processing. This raises many concerns from various perspectives, e.g., financial costs and carbon emissions. Compressing PLMs like BERT with negligible performance loss for faster inference and cheaper deployment has attracted much attention. In this work, we aim to explore larger compression ratios for PLMs, among which tensor decomposition is a potential but under-investigated one. Two decomposition and reconstruction protocols are further proposed to improve the effectiveness and efficiency during compression. Our compressed BERT with ${1}/{7}$ parameters in Transformer layers performs on-par with, sometimes slightly better than the original BERT in GLUE benchmark. A tiny version achieves $96.7\%$ performance of BERT-base with $ {1}/{48} $ encoder parameters (i.e., less than 2M parameters excluding the embedding layer) and $2.7 \times$ faster on inference. To show that the proposed method is orthogonal to existing compression methods like knowledge distillation, we also explore the benefit of the proposed method on a distilled BERT.

arXiv:2205.09191

High-Order Multilinear Discriminant Analysis via Order-$\textit{n}$ Tensor Eigendecomposition

Higher-order data with high dimensionality is of immense importance in many areas of machine learning, computer vision, and video analytics. Multidimensional arrays (commonly referred to as tensors) are used for arranging higher-order data structures while keeping the natural representation of the data samples. In the past decade, great efforts have been made to extend the classic linear discriminant analysis for higher-order data classification generally referred to as multilinear discriminant analysis (MDA). Most of the existing approaches are based on the Tucker decomposition and $\textit{n}$-mode tensor-matrix products. The current paper presents a new approach to tensor-based multilinear discriminant analysis referred to as High-Order Multilinear Discriminant Analysis (HOMLDA). This approach is based upon the tensor decomposition where an order-$\textit{n}$ tensor can be written as a product of order-$\textit{n}$ tensors and has a natural extension to traditional linear discriminant analysis (LDA). Furthermore, the resulting framework, HOMLDA, might produce a within-class scatter tensor that is close to singular. Thus, computing the inverse inaccurately may distort the discriminant analysis. To address this problem, an improved method referred to as Robust High-Order Multilinear Discriminant Analysis (RHOMLDA) is introduced. Experimental results on multiple data sets illustrate that our proposed approach provides improved classification performance with respect to the current Tucker decomposition-based supervised learning methods.

arXiv:2205.06407

Tensor Decompositions for Hyperspectral Data Processing in Remote Sensing: A Comprehensive Review

Owing to the rapid development of sensor technology, hyperspectral (HS) remote sensing (RS) imaging has provided a significant amount of spatial and spectral information for the observation and analysis of the Earth's surface at a distance of data acquisition devices, such as aircraft, spacecraft, and satellite. The recent advancement and even revolution of the HS RS technique offer opportunities to realize the full potential of various applications, while confronting new challenges for efficiently processing and analyzing the enormous HS acquisition data. Due to the maintenance of the 3-D HS inherent structure, tensor decomposition has aroused widespread concern and research in HS data processing tasks over the past decades. In this article, we aim at presenting a comprehensive overview of tensor decomposition, specifically contextualizing the five broad topics in HS data processing, and they are HS restoration, compressed sensing, anomaly detection, super-resolution, and spectral unmixing. For each topic, we elaborate on the remarkable achievements of tensor decomposition models for HS RS with a pivotal description of the existing methodologies and a representative exhibition on the experimental results. As a result, the remaining challenges of the follow-up research directions are outlined and discussed from the perspective of the real HS RS practices and tensor decomposition merged with advanced priors and even with deep neural networks. This article summarizes different tensor decomposition-based HS data processing methods and categorizes them into different classes from simple adoptions to complex combinations with other priors for the algorithm beginners. We also expect this survey can provide new investigations and development trends for the experienced researchers who understand tensor decomposition and HS RS to some extent.

arXiv:2205.03798

Fast and Structured Block-Term Tensor Decomposition For Hyperspectral Unmixing

The block-term tensor decomposition model with multilinear rank-$(L_r,L_r,1)$ terms (or, the "LL1 tensor decomposition" in short) offers a valuable alternative for hyperspectral unmixing (HU) under the linear mixture model. Particularly, the LL1 decomposition ensures the endmember/abundance identifiability in scenarios where such guarantees are not supported by the classic matrix factorization (MF) approaches. However, existing LL1-based HU algorithms use a three-factor parameterization of the tensor (i.e., the hyperspectral image cube), which leads to a number of challenges including high per-iteration complexity, slow convergence, and difficulties in incorporating structural prior information. This work puts forth an LL1 tensor decomposition-based HU algorithm that uses a constrained two-factor re-parameterization of the tensor data. As a consequence, a two-block alternating gradient projection (GP)-based LL1 algorithm is proposed for HU. With carefully designed projection solvers, the GP algorithm enjoys a relatively low per-iteration complexity. Like in MF-based HU, the factors under our parameterization correspond to the endmembers and abundances. Thus, the proposed framework is natural to incorporate physics-motivated priors that arise in HU. The proposed algorithm often attains orders-of-magnitude speedup and substantial HU performance gains compared to the existing three-factor parameterization-based HU algorithms.