Graph Neural Networks (GNNs) have become the de facto standard for analyzing graph-structured data, leveraging message-passing techniques to capture both structural and node feature information. However, recent studies have raised concerns about the statistical reliability of uncertainty estimates produced by GNNs. This paper addresses this crucial challenge by introducing a novel technique for quantifying uncertainty in non-exchangeable graph-structured data, while simultaneously reducing the size of label prediction sets in graph classification tasks. We propose Conformalized Tensor-based Topological Neural Networks (CF-T2NN), a new approach for rigorous prediction inference over graphs. CF-T2NN employs tensor decomposition and topological knowledge learning to navigate and interpret the inherent uncertainty in decision-making processes. This method enables a more nuanced understanding and handling of prediction uncertainties, enhancing the reliability and interpretability of neural network outcomes. Our empirical validation, conducted across 10 real-world datasets, demonstrates the superiority of CF-T2NN over a wide array of state-of-the-art methods on various graph benchmarks. This work not only enhances the GNN framework with robust uncertainty quantification capabilities but also sets a new standard for reliability and precision in graph-structured data analysis.
This paper presents a canonical polyadic (CP) tensor decomposition that addresses unaligned observations. The mode with unaligned observations is represented using functions in a reproducing kernel Hilbert space (RKHS). We introduce a versatile loss function that effectively accounts for various types of data, including binary, integer-valued, and positive-valued types. Additionally, we propose an optimization algorithm for computing tensor decompositions with unaligned observations, along with a stochastic gradient method to enhance computational efficiency. A sketching algorithm is also introduced to further improve efficiency when using the $\ell_2$ loss function. To demonstrate the efficacy of our methods, we provide illustrative examples using both synthetic data and an early childhood human microbiome dataset.
Convolutional neural networks (CNNs) have made significant advances in computer vision tasks, yet their high inference times and latency often limit real-world applicability. While model compression techniques have gained popularity as solutions, they often overlook the critical balance between low latency and uncompromised accuracy. By harnessing quantum-inspired pruning, tensor decomposition, and annealing-based matrix factorization - three quantum-inspired concepts - we introduce QIANets: a novel approach of redesigning the traditional GoogLeNet, DenseNet, and ResNet-18 model architectures to process more parameters and computations whilst maintaining low inference times. Despite experimental limitations, the method was tested and evaluated, demonstrating reductions in inference times, along with effective accuracy preservations.
We propose ESPACE, an LLM compression technique based on dimensionality reduction of activations. Unlike prior works on weight-centric tensor decomposition, ESPACE projects activations onto a pre-calibrated set of principal components. The activation-centrality of the approach enables retraining LLMs with no loss of expressivity; while at inference, weight decomposition is obtained as a byproduct of matrix multiplication associativity. Theoretical results on the construction of projection matrices with optimal computational accuracy are provided. Experimentally, we find ESPACE enables 50% compression of GPT3, Llama2, and Nemotron4 models with small accuracy degradation, as low as a 0.18 perplexity increase on GPT3-22B. At lower compression rates of 20% to 40%, ESPACE drives GPT3 models to outperforming their baseline, by up to a 0.38 decrease in perplexity for GPT3-8B. ESPACE also reduces GEMM execution time and prefill inference latency on existing hardware. Comparison with related works on compressing Llama2-7B via matrix factorization shows that ESPACE is a first step in advancing the state-of-the-art in tensor decomposition compression of LLMs.
The advent of artificial intelligence in medical imaging has paved the way for significant advancements in the diagnosis of brain tumors. This study presents a novel ensemble approach that uses magnetic resonance imaging (MRI) to identify and categorize common brain cancers, such as pituitary, meningioma, and glioma. The proposed workflow is composed of a two-fold approach: firstly, it employs non-trivial image enhancement techniques in data preprocessing, low-rank Tucker decomposition for dimensionality reduction, and machine learning (ML) classifiers to detect and predict the type of brain tumor. Secondly, persistent homology (PH), a topological data analysis (TDA) technique, is exploited to extract potential critical areas in MRI scans. When paired with the ML classifier output, this additional information can help domain experts to identify areas of interest that might contain tumor signatures, improving the interpretability of ML predictions. When compared to automated diagnoses, this transparency adds another level of confidence and is essential for clinical acceptance. The performance of the system was quantitatively evaluated on a well-known MRI dataset, with an overall classification accuracy of 97.28% using an extremely randomized trees model. The promising results show that the integration of TDA, ML, and low-rank approximation methods is a successful approach for brain tumor identification and categorization, providing a solid foundation for further study and clinical application.
Nearest-neighbor search in large vector databases is crucial for various machine learning applications. This paper introduces a novel method using tensor-train (TT) low-rank tensor decomposition to efficiently represent point clouds and enable fast approximate nearest-neighbor searches. We propose a probabilistic interpretation and utilize density estimation losses like Sliced Wasserstein to train TT decompositions, resulting in robust point cloud compression. We reveal an inherent hierarchical structure within TT point clouds, facilitating efficient approximate nearest-neighbor searches. In our paper, we provide detailed insights into the methodology and conduct comprehensive comparisons with existing methods. We demonstrate its effectiveness in various scenarios, including out-of-distribution (OOD) detection problems and approximate nearest-neighbor (ANN) search tasks.
Matrix and tensor-guided parametrization for Natural Language Processing (NLP) models is fundamentally useful for the improvement of the model's systematic efficiency. However, the internal links between these two algebra structures and language model parametrization are poorly understood. Also, the existing matrix and tensor research is math-heavy and far away from machine learning (ML) and NLP research concepts. These two issues result in the recent progress on matrices and tensors for model parametrization being more like a loose collection of separate components from matrix/tensor and NLP studies, rather than a well-structured unified approach, further hindering algorithm design. To this end, we propose a unified taxonomy, which bridges the matrix/tensor compression approaches and model compression concepts in ML and NLP research. Namely, we adopt an elementary concept in linear algebra, that of a subspace, which is also the core concept in geometric algebra, to reformulate the matrix/tensor and ML/NLP concepts (e.g. attention mechanism) under one umbrella. In this way, based on our subspace formalization, typical matrix and tensor decomposition algorithms can be interpreted as geometric transformations. Finally, we revisit recent literature on matrix- or tensor-guided language model compression, rephrase and compare their core ideas, and then point out the current research gap and potential solutions.
We propose a new operator defined between two tensors, the broadcast product. The broadcast product calculates the Hadamard product after duplicating elements to align the shapes of the two tensors. Complex tensor operations in libraries like \texttt{numpy} can be succinctly represented as mathematical expressions using the broadcast product. Finally, we propose a novel tensor decomposition using the broadcast product, highlighting its potential applications in dimensionality reduction.
Tensor decomposition has emerged as a prominent technique to learn low-dimensional representation under the supervision of reconstruction error, primarily benefiting data inference tasks like completion and imputation, but not classification task. We argue that the non-uniqueness and rotation invariance of tensor decomposition allow us to identify the directions with largest class-variability and simple graph Laplacian can effectively achieve this objective. Therefore we propose a novel Pseudo Laplacian Contrast (PLC) tensor decomposition framework, which integrates the data augmentation and cross-view Laplacian to enable the extraction of class-aware representations while effectively capturing the intrinsic low-rank structure within reconstruction constraint. An unsupervised alternative optimization algorithm is further developed to iteratively estimate the pseudo graph and minimize the loss using Alternating Least Square (ALS). Extensive experimental results on various datasets demonstrate the effectiveness of our approach.
Anomaly detection (AD) is increasingly recognized as a key component for ensuring the resilience of future communication systems. While deep learning has shown state-of-the-art AD performance, its application in critical systems is hindered by concerns regarding training data efficiency, domain adaptation and interpretability. This work considers AD in network flows using incomplete measurements, leveraging a robust tensor decomposition approach and deep unrolling techniques to address these challenges. We first propose a novel block-successive convex approximation algorithm based on a regularized model-fitting objective where the normal flows are modeled as low-rank tensors and anomalies as sparse. An augmentation of the objective is introduced to decrease the computational cost. We apply deep unrolling to derive a novel deep network architecture based on our proposed algorithm, treating the regularization parameters as learnable weights. Inspired by Bayesian approaches, we extend the model architecture to perform online adaptation to per-flow and per-time-step statistics, improving AD performance while maintaining a low parameter count and preserving the problem's permutation equivariances. To optimize the deep network weights for detection performance, we employ a homotopy optimization approach based on an efficient approximation of the area under the receiver operating characteristic curve. Extensive experiments on synthetic and real-world data demonstrate that our proposed deep network architecture exhibits a high training data efficiency, outperforms reference methods, and adapts seamlessly to varying network topologies.
Despite their high accuracy, complex neural networks demand significant computational resources, posing challenges for deployment on resource-constrained devices such as mobile phones and embedded systems. Compression algorithms have been developed to address these challenges by reducing model size and computational demands while maintaining accuracy. Among these approaches, factorization methods based on tensor decomposition are theoretically sound and effective. However, they face difficulties in selecting the appropriate rank for decomposition. This paper tackles this issue by presenting a unified framework that simultaneously applies decomposition and optimal rank selection, employing a composite compression loss within defined rank constraints. Our approach includes an automatic rank search in a continuous space, efficiently identifying optimal rank configurations without the use of training data, making it computationally efficient. Combined with a subsequent fine-tuning step, our approach maintains the performance of highly compressed models on par with their original counterparts. Using various benchmark datasets, we demonstrate the efficacy of our method through a comprehensive analysis.
Deep neural networks typically impose significant computational loads and memory consumption. Moreover, the large parameters pose constraints on deploying the model on edge devices such as embedded systems. Tensor decomposition offers a clear advantage in compressing large-scale weight tensors. Nevertheless, direct utilization of low-rank decomposition typically leads to significant accuracy loss. This paper proposes a model compression method that integrates Variational Bayesian Matrix Factorization (VBMF) with orthogonal regularization. Initially, the model undergoes over-parameterization and training, with orthogonal regularization applied to enhance its likelihood of achieving the accuracy of the original model. Secondly, VBMF is employed to estimate the rank of the weight tensor at each layer. Our framework is sufficiently general to apply to other convolutional neural networks and easily adaptable to incorporate other tensor decomposition methods. Experimental results show that for both high and low compression ratios, our compression model exhibits advanced performance.
Physics-Informed Neural Networks (PINNs) have shown continuous and increasing promise in approximating partial differential equations (PDEs), although they remain constrained by the curse of dimensionality. In this paper, we propose a generalized PINN version of the classical variable separable method. To do this, we first show that, using the universal approximation theorem, a multivariate function can be approximated by the outer product of neural networks, whose inputs are separated variables. We leverage tensor decomposition forms to separate the variables in a PINN setting. By employing Canonic Polyadic (CP), Tensor-Train (TT), and Tucker decomposition forms within the PINN framework, we create robust architectures for learning multivariate functions from separate neural networks connected by outer products. Our methodology significantly enhances the performance of PINNs, as evidenced by improved results on complex high-dimensional PDEs, including the 3d Helmholtz and 5d Poisson equations, among others. This research underscores the potential of tensor decomposition-based variably separated PINNs to surpass the state-of-the-art, offering a compelling solution to the dimensionality challenge in PDE approximation.
The canonical polyadic (CP) tensor decomposition decomposes a multidimensional data array into a sum of outer products of finite-dimensional vectors. Instead, we can replace some or all of the vectors with continuous functions (infinite-dimensional vectors) from a reproducing kernel Hilbert space (RKHS). We refer to tensors with some infinite-dimensional modes as quasitensors, and the approach of decomposing a tensor with some continuous RKHS modes is referred to as CP-HiFi (hybrid infinite and finite dimensional) tensor decomposition. An advantage of CP-HiFi is that it can enforce smoothness in the infinite dimensional modes. Further, CP-HiFi does not require the observed data to lie on a regular and finite rectangular grid and naturally incorporates misaligned data. We detail the methodology and illustrate it on a synthetic example.
This paper addresses the channel estimation problem for beyond diagonal reconfigurable intelligent surface (BD-RIS) from a tensor decomposition perspective. We first show that the received pilot signals can be arranged as a three-way tensor, allowing us to recast the cascaded channel estimation problem as a block Tucker decomposition problem that yields decoupled estimates for the involved channel matrices while offering a substantial performance gain over the conventional (matrix-based) least squares (LS) estimation method. More specifically, we develop two solutions to solve the problem. The first one is a closed-form solution that extracts the channel estimates via a block Tucker Kronecker factorization (BTKF), which boils down to solving a set of parallel rank-one matrix approximation problems. Exploiting such a low-rank property yields a noise rejection gain compared to the standard LS estimation scheme while allowing the two involved channels to be estimated separately. The second solution is based on a block Tucker alternating least squares (BTALS) algorithm that directly estimates the involved channel matrices using an iterative estimation procedure. We discuss the uniqueness and identifiability issues and their implications for training design. We also propose a tensor-based design of the BD-RIS training tensor for each algorithm that ensures unique decoupled channel estimates under trivial scaling ambiguities. Our numerical results shed light on the tradeoffs offered by BTKF and BTALS methods. Specifically, while the first enjoys fast and parallel extraction of the channel estimates in closed form, the second has a more flexible training design, allowing for a significantly reduced training overhead compared to the state-of-the-art LS method.
The fast development of object detection techniques has attracted attention to developing efficient Deep Neural Networks (DNNs). However, the current state-of-the-art DNN models can not provide a balanced solution among accuracy, speed, and model size. This paper proposes an efficient real-time object detection framework on resource-constrained hardware devices through hardware and software co-design. The Tensor Train (TT) decomposition is proposed for compressing the YOLOv5 model. By unitizing the unique characteristics given by the TT decomposition, we develop an efficient hardware accelerator based on FPGA devices. Experimental results show that the proposed method can significantly reduce the model size and improve the execution time.
In this letter, we investigate the channel estimation problem for MIMO wireless communication systems with movable antennas (MAs) at both the transmitter (Tx) and receiver (Rx). To achieve high channel estimation accuracy with low pilot training overhead, we propose a tensor decomposition-based method for estimating the parameters of multi-path channel components, including their azimuth and elevation angles, as well as complex gain coefficients, thereby reconstructing the wireless channel between any pair of Tx and Rx MA positions in the Tx and Rx regions. First, we introduce a two-stage Tx-Rx successive antenna movement pattern for pilot training, such that the received pilot signals in both stages can be expressed as a third-order tensor. Then, we obtain the factor matrices of the tensor via the canonical polyadic decomposition, and thereby estimate the angle/gain parameters for enabling the channel reconstruction between arbitrary Tx/Rx MA positions. In addition, we analyze the uniqueness condition of the tensor decomposition, which ensures the complete channel reconstruction between the whole Tx and Rx regions based on the channel measurements at only a finite number of Tx/Rx MA positions. Finally, simulation results are presented to evaluate the proposed tensor decomposition-based method as compared to existing methods, in terms of channel estimation accuracy and pilot overhead.
Recently, introducing Tensor Decomposition (TD) methods into unsupervised feature selection (UFS) has been a rising research point. A tensor structure is beneficial for mining the relations between different modes and helps relieve the computation burden. However, while existing methods exploit TD to minimize the reconstruction error of a data tensor, they don't fully utilize the interpretable and discriminative information in the factor matrices. Moreover, most methods require domain knowledge to perform feature selection. To solve the above problems, we develop two Sparse Tensor Principal Component Analysis (STPCA) models that utilize the projection directions in the factor matrices to perform UFS. The first model extends Tucker Decomposition to a multiview sparse regression form and is transformed into several alternatively solved convex subproblems. The second model formulates a sparse version of the family of Tensor Singular Value Decomposition (T-SVDs) and is transformed into individual convex subproblems. For both models, we prove the optimal solution of each subproblem falls onto the Hermitian Positive Semidefinite Cone (HPSD). Accordingly, we design two fast algorithms based on HPSD projection and prove their convergence. According to the experimental results on two original synthetic datasets (Orbit and Array Signal) and five real-world datasets, the two proposed methods are suitable for handling different data tensor scenarios and outperform the state-of-the-art UFS methods.
Infrared small target detection is crucial for the efficacy of infrared search and tracking systems. Current tensor decomposition methods emphasize representing small targets with sparsity but struggle to separate targets from complex backgrounds due to insufficient use of intrinsic directional information and reduced target visibility during decomposition. To address these challenges, this study introduces a Sparse Differential Directionality prior (SDD) framework. SDD leverages the distinct directional characteristics of targets to differentiate them from the background, applying mixed sparse constraints on the differential directional images and continuity difference matrix of the temporal component, both derived from Tucker decomposition. We further enhance target detectability with a saliency coherence strategy that intensifies target contrast against the background during hierarchical decomposition. A Proximal Alternating Minimization-based (PAM) algorithm efficiently solves our proposed model. Experimental results on several real-world datasets validate our method's effectiveness, outperforming ten state-of-the-art methods in target detection and clutter suppression. Our code is available at https://github.com/GrokCV/SDD.
Large neural networks have aroused impressive progress in various real world applications. However, the expensive storage and computational resources requirement for running deep networks make them problematic to be deployed on mobile devices. Recently, matrix and tensor decompositions have been employed for compressing neural networks. In this paper, we develop a simultaneous tensor decomposition technique for network optimization. The shared network structure is first discussed. Sometimes, not only the structure but also the parameters are shared to form a compressed model at the expense of degraded performance. This indicates that the weight tensors between layers within one network contain both identical components and independent components. To utilize this characteristic, two new coupled tensor train decompositions are developed for fully and partly structure sharing cases, and an alternating optimization approach is proposed for low rank tensor computation. Finally, we restore the performance of the neural network model by fine-tuning. The compression ratio of the devised approach can then be calculated. Experimental results are also included to demonstrate the benefits of our algorithm for both applications of image reconstruction and classification, using the well known datasets such as Cifar-10/Cifar-100 and ImageNet and widely used networks such as ResNet. Comparing to the state-of-the-art independent matrix and tensor decomposition based methods, our model can obtain a better network performance under the same compression ratio.