Related papers: Tensor Train decomposition on TensorFlow (T3F)

Deep learning models with convolutional and recurrent networks are now ubiquitous and analyze massive amounts of audio, image, video, text and graph data, with applications in automatic translation, speech-to-text, scene understanding,…

Tucker decomposition is one of the SOTA CNN model compression techniques. However, unlike the FLOPs reduction, we observe very limited inference time reduction with Tucker-compressed models using existing GPU software such as cuDNN. To this…

Machine learning and data mining algorithms are becoming increasingly important in analyzing large volume, multi-relational and multi--modal datasets, which are often conveniently represented as multiway arrays or tensors. It is therefore…

Tensors with unit Frobenius norm are fundamental objects in many fields, including scientific computing and quantum physics, which are able to represent normalized eigenvectors and pure quantum states. While the tensor train decomposition…

With the advent of GPU-assisted hardware and maturing high-efficiency software platforms such as TensorFlow and PyTorch, Bayesian posterior sampling for neural networks becomes plausible. In this article we discuss Bayesian parametrization…

We present Neural Feature Fusion Fields (N3F), a method that improves dense 2D image feature extractors when the latter are applied to the analysis of multiple images reconstructible as a 3D scene. Given an image feature extractor, for…

The deployment of convolutional neural networks is often hindered by high computational and storage requirements. Structured model pruning is a promising approach to alleviate these requirements. Using the VGG-16 model as an example, we…

State-of-the-art federated learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. For neural networks, even when centralized SGD easily finds a solution that is…

Tensor computation has emerged as a powerful mathematical tool for solving high-dimensional and/or extreme-scale problems in science and engineering. The last decade has witnessed tremendous advancement of tensor computation and its…

In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF). It leverages recent advances of various network compression methods and implements some…

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…

We have applied Google's TensorFlow deep learning toolkit to recognize the visualized results of the fragment molecular orbital (FMO) calculations. Typical protein structures of alpha-helix and beta-sheet provide some characteristic…

Graph Neural Networks (GNNs) have emerged as the leading paradigm for learning over graph-structured data. However, their performance is limited by issues inherent to graph topology, most notably oversquashing and oversmoothing. Recent…

This paper undertakes the task of replicating the MaskFormer model a universal image segmentation model originally developed using the PyTorch framework, within the TensorFlow ecosystem, specifically optimized for execution on Tensor…

Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML…

A series of graph filtering (GF)-based collaborative filtering (CF) showcases state-of-the-art performance on the recommendation accuracy by using a low-pass filter (LPF) without a training process. However, conventional GF-based CF…

The tensor train decomposition decomposes a tensor into a "train" of 3-way tensors that are interconnected through the summation of auxiliary indices. The decomposition is stable, has a well-defined notion of rank and enables the user to…

Tensor train decomposition is widely used in machine learning and quantum physics due to its concise representation of high-dimensional tensors, overcoming the curse of dimensionality. Cross approximation-originally developed for…

Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of raw data in centralized methods. However, these FL methods…

Extracting information about dynamical systems from models learned off simulation data has become an increasingly important research topic in the natural and engineering sciences. Modeling the Koopman operator semigroup has played a central…