LAUSR

About LAUSR
Donate
Contact Us

Follow us:

You are not signed in:

Sign Up!


   Articles with "sparsification" as a keyword



Deep Learning of Sparse Patterns in Medical IoT for Efficient Big Data Harnessing

Sign Up to like & get
recommendations! Published in 2023 at "IEEE Access"

DOI: 10.1109/access.2023.3256721

Abstract: The long-term and continuous streaming of big data from medical Internet of Things (IoT), poses a great challenge for the battery-limited tiny devices. To address this challenge, we propose a novel framework for medical IoT… read more here.

Keywords: sparsification; big data; medical iot; deep learning ... See more keywords

ELO-Mask: Effective and Layerwise Optimization of Mask for Sparse LLMs

Sign Up to like & get
recommendations! Published in 2024 at "IEEE Access"

DOI: 10.1109/access.2024.3498904

Abstract: To address the issue of the substantial computational resource consumption during the inference phase of large language models due to their vast number of parameters, model sparsification is an effective solution. However, current sparsification methods… read more here.

Keywords: elo mask; step; sparsification; language ... See more keywords

Communication-Adaptive-Gradient Sparsification for Federated Learning With Error Compensation

Sign Up to like & get
recommendations! Published in 2025 at "IEEE Internet of Things Journal"

DOI: 10.1109/jiot.2024.3490855

Abstract: Federated learning (FL) has emerged as a popular distributed machine-learning paradigm. It involves many rounds of iterative communication between nodes to exchange model parameters. With the increasing complexity of ML tasks, the models can be… read more here.

Keywords: cost; sparsification; error compensation; proposed algorithm ... See more keywords

Graph SLAM Sparsification With Populated Topologies Using Factor Descent Optimization

Sign Up to like & get
recommendations! Published in 2018 at "IEEE Robotics and Automation Letters"

DOI: 10.1109/lra.2018.2798283

Abstract: Current solutions to the simultaneous localization and mapping (SLAM) problem approach it as the optimization of a graph of geometric constraints. Scalability is achieved by reducing the size of the graph, usually in two phases.… read more here.

Keywords: factor descent; populated topologies; slam sparsification; optimization ... See more keywords

Model Compression via Pattern Shared Sparsification in Analog Federated Learning Under Communication Constraints

Sign Up to like & get
recommendations! Published in 2023 at "IEEE Transactions on Green Communications and Networking"

DOI: 10.1109/tgcn.2022.3186538

Abstract: Recently, it has been shown that analog transmission based federated learning enables more efficient usage of communication resources compared to the conventional digital transmission. In this paper, we propose an effective model compression strategy enabling… read more here.

Keywords: shared sparsification; analog; sparsification; communication ... See more keywords
Photo from wikipedia

Reducing the Complexity of Model-Based MRI Reconstructions via Sparsification

Sign Up to like & get
recommendations! Published in 2021 at "IEEE Transactions on Medical Imaging"

DOI: 10.1109/tmi.2021.3081013

Abstract: Model-based reconstruction methods have emerged as a powerful alternative to classical Fourier-based MRI techniques, largely because of their ability to explicitly model (and therefore, potentially overcome) moderate field inhomogeneities, streamline reconstruction from non-Cartesian sampling, and… read more here.

Keywords: reconstruction; model based; model; complexity ... See more keywords

Co-Exploring Structured Sparsification and Low-Rank Tensor Decomposition for Compact DNNs

Sign Up to like & get
recommendations! Published in 2024 at "IEEE Transactions on Neural Networks and Learning Systems"

DOI: 10.1109/tnnls.2024.3408099

Abstract: Sparsification and low-rank decomposition are two important techniques to compress deep neural network (DNN) models. To date, these two popular yet distinct approaches are typically used in separate ways; while their efficient integration for better… read more here.

Keywords: structured sparsification; sparsification; tensor decomposition; sparsification low ... See more keywords

Error-Compensated Sparsification for Communication-Efficient Decentralized Training in Edge Environment

Sign Up to like & get
recommendations! Published in 2021 at "IEEE Transactions on Parallel and Distributed Systems"

DOI: 10.1109/tpds.2021.3084104

Abstract: Communication has been considered as a major bottleneck in large-scale decentralized training systems since participating nodes iteratively exchange large amounts of intermediate data with their neighbors. Although compression techniques like sparsification can significantly reduce the… read more here.

Keywords: error compensated; communication; decentralized training; compensated sparsification ... See more keywords

MIPD: An Adaptive Gradient Sparsification Framework for Distributed DNNs Training

Sign Up to like & get
recommendations! Published in 2022 at "IEEE Transactions on Parallel and Distributed Systems"

DOI: 10.1109/tpds.2022.3154387

Abstract: Asynchronous training is widely used for scaling DNN training over large-scale distributed deep learning systems using the parameter server architecture. Communication has been identified as the bottleneck, since large volumes of data are exchanged during… read more here.

Keywords: sparsification; mipd adaptive; framework; sparsification framework ... See more keywords

Sparsification of long range force networks for molecular dynamics simulations

Sign Up to like & get
recommendations! Published in 2019 at "PLoS ONE"

DOI: 10.1371/journal.pone.0213262

Abstract: Atomic interactions in solid materials are described using network theory. The tools of network theory focus on understanding the properties of a system based upon the underlying interactions which govern their dynamics. While the full… read more here.

Keywords: spectral sparsification; network; sparsification long; force ... See more keywords

EVFL: Towards Efficient Verifiable Federated Learning via Parameter Reuse and Adaptive Sparsification

Sign Up to like & get
recommendations! Published in 2024 at "Mathematics"

DOI: 10.3390/math12162479

Abstract: Federated learning (FL) demonstrates significant potential in Industrial Internet of Things (IIoT) settings, as it allows multiple institutions to jointly construct a shared learning model by exchanging model parameters or gradient updates without the need… read more here.

Keywords: evfl towards; parameter; sparsification; federated learning ... See more keywords