A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems
[article]
2020
arXiv
pre-print
Preserved Fulltext
This paper provides a high-level introduction to meta-learning with applications to communication systems. ...
With a meta-trained inductive bias, training of a machine learning model can be potentially carried out with reduced training data and/or time complexity. ...
FROM LEARNING TO META-LEARNING Protocols and algorithms for communication networks are expected to operate in a variety of system configurations. ...
arXiv:2001.01227v1
fatcat:itszjmo4gzfzrf2w5tnlbqd4tu
Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:1908.09049v2 fatcat:hgmej45vnfbu7o7fhssvbu3mtyOther Versions
Accordingly, pilots from previous IoT transmissions are used as meta-training data in order to train a demodulator that is able to quickly adapt to new end-to-end channel conditions from few pilots. ...
Various state-of-the-art meta-learning schemes are adapted to the problem at hand and evaluated, including Model-Agnostic Meta-Learning (MAML), First-Order MAML (FOMAML), REPTILE, and fast Context Adaptation ...
Reference [13] provides a review of meta-learning with applications to communication systems. ...
arXiv:1908.09049v3
fatcat:2nfbvcze4rghrgk5w5i32tehie
Knowledge-driven Meta-learning for CSI Feedback
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2023 pre-print arXiv:2310.15548v1 fatcat:vav6cxgbvnerzi2g2cm4khrkkm
In this article, a knowledge-driven meta-learning approach is proposed, where the DL model initialized by the meta model obtained from meta training phase is able to achieve rapid convergence when facing ...
Recently, deep learning (DL) has been introduced for CSI feedback enhancement through massive collected training data and lengthy training time, which is quite costly and impractical for realistic deployment ...
In section II, we introduce the system model and formulate the problem of meta learning to be solved for CSI feedback. ...
arXiv:2310.15548v2
fatcat:mj5gblcwzvautiaslon5krcuaa
Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning
[article]
2024
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Federated learning is a new learning paradigm that decouples data collection and model training via multi-party computation and model aggregation. ...
Following the emerging trends, we also discuss federated learning in the intersection with other learning paradigms, termed federated X learning, where X includes multitask learning, meta-learning, transfer ...
Communication Efficiency Communication efficiency is a challenging research direction in federated learning, which typically focuses on reducing the communication overhead between clients and servers, ...
arXiv:2102.12920v5
fatcat:5bfsderk7nbcllse7akyj7mv3a
Fast Meta Learning for Adaptive Beamforming
2021
ICC 2021 - IEEE International Conference on Communications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Simulation results demonstrate that compared to the state of the art meta learning method, our proposed algorithm reduces the complexities in both training and adaptation processes by more than an order ...
This paper studies the deep learning based adaptive downlink beamforming solution for the signal-to-interferenceplus-noise ratio balancing problem. ...
(5G) and beyond communications systems. ...
doi:10.1109/icc42927.2021.9500589
fatcat:4rleerxwd5cr5p4jypyxnjyw5e
Federated Meta-Learning with Fast Convergence and Efficient Communication
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this work, we show that meta-learning is a natural choice to handle these issues, and propose a federated meta-learning framework FedMeta, where a parameterized algorithm (or meta-learner) is shared ...
Statistical and systematic challenges in collaboratively training machine learning models across distributed networks of mobile devices have been the bottlenecks in the real-world application of federated ...
and system overhead. ...
arXiv:1802.07876v2
fatcat:gpi4ck56zbcnzopiraek5jabhe
TinyMetaFed: Efficient Federated Meta-Learning for TinyML
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The evaluations on three TinyML use cases demonstrate that TinyMetaFed can significantly reduce energy consumption and communication overhead, accelerate convergence, and stabilize the training process ...
We introduce TinyMetaFed, a model-agnostic meta-learning framework suitable for TinyML. ...
: Meta Operating Systems". ...
arXiv:2307.06822v3
fatcat:mitfkkicivf7zh4nxiowmjobgy
Meta-Learning with Differentiable Convex Optimization
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. ...
We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition ...
Also, we appreciate the anonymous reviewers for their helpful and constructive comments and suggestions. Finally, we would like to thank Chuyi Sun for help with Figure 1 . ...
arXiv:1904.03758v2
fatcat:lgpeaofwhnf7bjdf6h2d7qpnd4
Meta-Learning With Differentiable Convex Optimization
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. ...
We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition ...
Also, we appreciate the anonymous reviewers for their helpful and constructive comments and suggestions. Finally, we would like to thank Chuyi Sun for help with Figure 1 . ...
doi:10.1109/cvpr.2019.01091
dblp:conf/cvpr/LeeMRS19
fatcat:gcrmqlejsrdgdnrnrtp5zhcq6a
Efficient Cross-Project Software Defect Prediction Based on Federated Meta-Learning
2024
Electronics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
By learning common knowledge on the local data of multiple clients, and then fine-tuning the model, the number of unnecessary iterations is reduced, and communication efficiency is improved while reducing ...
Focusing on the model performance and communication efficiency of cross-project software defect prediction, this paper proposes an efficient communication-based federated meta-learning (ECFML) algorithm ...
Lightweight models can reduce the size and computational complexity of the model, thereby reducing the amount of data transmi ed between devices and communication overhead. ...
doi:10.3390/electronics13061105
fatcat:vjnegvrd55d5xgdl5x5ogdayga
Learning from Few Examples: A Summary of Approaches to Few-Shot Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Few-Shot Learning refers to the problem of learning the underlying pattern in the data just from a few training samples. ...
Given the learning dynamics and characteristics, the approaches to few-shot learning problems are discussed in the perspectives of meta-learning, transfer learning, and hybrid approaches (i.e., different ...
Nonetheless, these techniques can be and often are meaningfully combined with meta-learning systems. ...
arXiv:2203.04291v1
fatcat:62alkjtmsvhxzij7vazb34n5re
Federated Learning and Meta Learning: Approaches, Applications, and Directions
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2210.13111v1 fatcat:2y55u5ym65h5hic2dx5uotblg4
In this tutorial, we present a comprehensive review of FL, meta learning, and federated meta learning (FedMeta). ...
Unlike other tutorial papers, our objective is to explore how FL, meta learning, and FedMeta methodologies can be designed, optimized, and evolved, and their applications over wireless networks. ...
Thus, it is difficult for meta learning to address complex datasets. ...
arXiv:2210.13111v2
fatcat:zssgrv77sjgk3h33xoi2dzvyw4
Online Meta-Learning For Hybrid Model-Based Deep Receivers
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our training mechanism uses a predictive meta-learning scheme to train rapidly from data corresponding to both current and past channel realizations. ...
To illustrate the proposed approach, we study DNN-aided receivers that utilize an interpretable model-based architecture, and introduce a modular training strategy based on predictive meta-learning. ...
In order to train effectively from short blocks in complex channels, we propose to incorporate long term relations by altering the setting of the hyperparameter θ j+1 via meta-learning.
B. ...
arXiv:2203.14359v2
fatcat:svpj4edzobck7cfxscuebyrvxa
Massive Data Generation for Deep Learning-aided Wireless Systems Using Meta Learning and Generative Adversarial Network
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To reduce the amount of training samples required for the wireless data generation, we train GAN with the help of the meta learning. ...
As an entirely-new paradigm to design the communication systems, deep learning (DL), an approach that the machine learns the desired wireless function, has received much attention recently. ...
The key idea behind the proposed D-WiDaC technique is to exploit CGAN and meta learning to reduce the training sample overhead. ...
arXiv:2208.11910v1
fatcat:ubciu4cchrcf3nzdwi3aljks5e
Meta-ViterbiNet: Online Meta-Learned Viterbi Equalization for Non-Stationary Channels
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
, optimizing the hyperparameters of the learning algorithm to facilitate rapid online adaptation; and 3) We adopt a decision-directed approach based on coded communications to enable online training with ...
to implement a model-based/data-driven equalizer, ViterbiNet, that operates with a relatively small number of trainable parameters; 2) We tailor a meta-learning procedure to the symbol detection problem ...
yields reduced BER as compared to joint learning; and its combination with meta-learning yields the lowest BER. ...
arXiv:2103.13483v1
fatcat:aswtyahhxbga3ogbz2wmafhrym
« Previous
Showing results 1 — 15 out of 1,041 results