8,630 Hits in 2.6 sec

Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models [article]

Zhengming Zhang, Yaoqing Yang, Zhewei Yao, Yujun Yan, Joseph E. Gonzalez, Michael W. Mahoney
2021 arXiv   pre-print
We call this learning problem semi-supervised federated learning (SSFL).  ...  First, we find that the so-called consistency regularization loss (CRL), which is widely used in semi-supervised learning, performs reasonably well but has large gradient diversity.  ...  Conclusions We studied the semi-supervised federated learning (SSFL) setting in which most samples are unlabeled.  ... 
arXiv:2008.11364v2 fatcat:ixy7htug7favtl6pjhogualbxa

Federated Semi-Supervised Multi-Task Learning to Detect COVID-19 and Lungs Segmentation Marking Using Chest Radiography Images and Raspberry Pi Devices: An Internet of Medical Things Application

Mahbub Ul Alam, Rahim Rahmani
2021 Sensors  
We also explore different cutting-edge machine learning techniques, such as federated learning, semi-supervised learning, transfer learning, and multi-task learning to explore the issue.  ...  Semi-Supervised Federated Learning This experiment uses all the training data distributed among different client devices to perform semi-supervised federated learning.  ...  In order to investigate the performance difference between semi-supervised federated learning and semi-supervised federated transfer learning, we have conducted two experiments.  ... 
doi:10.3390/s21155025 fatcat:zvpfhxtwvbfenoiuc75jj737py

Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling [article]

Tiantian Feng, Shrikanth Narayanan
2022 arXiv   pre-print
In this work, we propose a semi-supervised federated learning framework, Semi-FedSER, that utilizes both labeled and unlabeled data samples to address the challenge of limited labeled data samples in FL  ...  Federated learning (FL) is a distributed machine learning algorithm that coordinates clients to train a model collaboratively without sharing local data.  ...  Results Compared baselines We compare our semi-supervised learning framework with the following baselines: Supervised -Federated Here, we refer to supervised baseline as using only labeled data points  ... 
arXiv:2203.08810v1 fatcat:vg7shrkgcrht7lfxnbknc6qx54

SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labeling [article]

Haowen Lin, Jian Lou, Li Xiong, Cyrus Shahabi
2021 arXiv   pre-print
We propose a new framework dubbed SemiFed that unifies two dominant approaches for semi-supervised learning: consistency regularization and pseudo-labeling.  ...  We borrow ideas from semi-supervised learning methods where a large amount of unlabeled data is utilized to improve the model's accuracy despite limited access to labeled examples.  ...  [10] propose oneshot federated learning, where they let the server learn a successful global model over a network of federated devices in a single round of communication in both supervised and semi-supervised  ... 
arXiv:2108.09412v1 fatcat:4teau6zlubbzpcpgpx5bobmu2u

Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank [article]

Inigo Alonso, Alberto Sabater, David Ferstl, Luis Montesano, Ana C. Murillo
2021 arXiv   pre-print
Our approach outperforms the current state-of-the-art for semi-supervised semantic segmentation and semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most  ...  This work presents a novel approach for semi-supervised semantic segmentation.  ...  This work was partially funded by FEDER/ Ministerio de Ciencia, Innovación y Universidades/ Agencia Estatal de Investigación/RTC-2017-6421-7, PGC2018-098817-A-I00 and PID2019-105390RB-I00, Aragón regional  ... 
arXiv:2104.13415v3 fatcat:ggfxniy6ujfv5hykrjd6lq3gtq

Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phases [article]

Hasan Kassem, Deepak Alapatt, Pietro Mascagni, AI4SafeChole Consortium, Alexandros Karargyris, Nicolas Padoy
2022 arXiv   pre-print
With these constraints in mind, we propose FedCy, a federated semi-supervised learning (FSSL) method that combines FL and self-supervised learning to exploit a decentralized dataset of both labeled and  ...  Recently proposed collaborative learning methods such as Federated Learning (FL) allow for training on remote datasets without the need to explicitly share data.  ...  Contributions Our work falls squarely at the intersection of federated and semi-supervised learning.  ... 
arXiv:2203.07345v1 fatcat:at5vffjlunghnm2on2hmig5dwe

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients [article]

Nan Lu, Zhao Wang, Xiaoxiao Li, Gang Niu, Qi Dou, Masashi Sugiyama
2022 arXiv   pre-print
Supervised federated learning (FL) enables multiple clients to share the trained model without sharing their labeled data.  ...  We propose federation of unsupervised learning (FedUL), where the unlabeled data are transformed into surrogate labeled data for each of the clients, a modified model is trained by supervised FL, and the  ...  B.2 SEMI-SUPERVISED FEDERATED LEARNING Another line of research working on utilizing unlabeled data in FL follows the semi-supervised learning framework (Zhu, 2005; Chapelle et al., 2006) , which assumes  ... 
arXiv:2204.03304v2 fatcat:5tbybbcsivdljkutjyj5r6vmai

FedTriNet: A Pseudo Labeling Method with Three Players for Federated Semi-supervised Learning [article]

Liwei Che and Zewei Long and Jiaqi Wang and Yaqing Wang and Houping Xiao and Fenglong Ma
2021 arXiv   pre-print
To tackle these issues, in this paper, we propose a novel federated semi-supervised learning method named FedTriNet, which consists of two learning phases.  ...  Most existing federated learning approaches focus on the supervised setting, which means all the data stored in each client has labels.  ...  Federated Semi-supervised Learning A more realistic setting in federated learning is federated semi-supervised learning, i.e., simultaneously considering both labeled and unlabeled data.  ... 
arXiv:2109.05612v2 fatcat:hp7rqaybwzfgjnlwi27vtb4lc4

Exploiting Unlabeled Data in Smart Cities using Federated Learning [article]

Abdullatif Albaseer, Bekir Sait Ciftler, Mohamed Abdallah, Ala Al-Fuqaha
2020 arXiv   pre-print
We propose a semi-supervised federated learning method called FedSem that exploits unlabeled data.  ...  In the second phase, we use semi-supervised learning based on the pseudo labeling technique to improve the model.  ...  FEDERATED SEMI-SUPERVISED LEARNING In this section, we explain the semi-supervised learning in general then, we narrow this definition to FL settings.  ... 
arXiv:2001.04030v2 fatcat:3rjaagqzfvdcnb3w2o5texlqha

Federated Self-Training for Semi-Supervised Audio Recognition [article]

Vasileios Tsouvalas, Aaqib Saeed, Tanir Ozcelebi
2022 arXiv   pre-print
In this work, we study the problem of semi-supervised learning of audio models via self-training in conjunction with federated learning.  ...  Most existing federated learning approaches focus on supervised learning without harnessing the unlabeled data.  ...  Semi-Supervised Learning.  ... 
arXiv:2107.06877v2 fatcat:hf3dr6i3n5c5bmzjkm6f2y3kei

Deep Semi-Supervised Learning for Time Series Classification [article]

Jann Goschenhofer, Rasmus Hvingelby, David Rügamer, Janek Thomas, Moritz Wagner, Bernd Bischl
2021 arXiv   pre-print
While Semi-supervised learning has gained much attention in computer vision on image data, yet limited research exists on its applicability in the time series domain.  ...  We find that these transferred semi-supervised models show significant performance gains over strong supervised, semi-supervised and self-supervised alternatives, especially for scenarios with very few  ...  This work was partially supported by the German Federal Ministry of Education and Research (BMBF) under Grant No. 01IS18036A.  ... 
arXiv:2102.03622v1 fatcat:t7arhdtrw5bz3lum7r7wgufygu

SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge Intelligence [article]

Arvin Tashakori, Wenwen Zhang, Z. Jane Wang, Peyman Servati
2022 arXiv   pre-print
This paper proposes a novel personalized semi-supervised federated learning (SemiPFL) framework to support edge users having no label or limited labeled datasets and a sizable amount of unlabeled data  ...  By leveraging personalized semi-supervised learning, SemiPFL dramatically reduces the need for annotating data and preserving privacy in a wide range of application scenarios, from wearable health to IoT  ...  There have been multiple attempts to unify federated learning with semi-supervised learning [28] , [33] , [48] .  ... 
arXiv:2203.08176v1 fatcat:3wotagtfcbf7ladgw44rllyn7i

High-Rankness Regularized Semi-Supervised Deep Metric Learning for Remote Sensing Imagery

Jian Kang, Rubén Fernández-Beltrán, Zhen Ye, Xiaohua Tong, Pedram Ghamisi, Antonio Plaza
2020 Remote Sensing  
To address this issue, we reformulate the deep metric learning scheme in a semi-supervised manner to effectively characterize RS scenes.  ...  Specifically, we aim at learning metric spaces by utilizing the supervised information from a small number of labeled RS images and exploring the potential decision boundaries for massive sets of unlabeled  ...  re-defines the standard deep metric learning framework by using an innovative semi-supervised design.  ... 
doi:10.3390/rs12162603 fatcat:2khmmy67vjbtnj7cct7jacngpe

Semi-Supervised Cross-Silo Advertising with Partial Knowledge Transfer [article]

Wenjie Li, Qiaolin Xia, Junfeng Deng, Hao Cheng, Jiangming Liu, Kouying Xue, Yong Cheng, Shu-Tao Xia
2022 arXiv   pre-print
In this paper, we propose a semi-supervised split distillation framework VFed-SSD to alleviate the two limitations.  ...  As an emerging secure learning paradigm in leveraging cross-agency private data, vertical federated learning (VFL) is expected to improve advertising models by enabling the joint learning of complementary  ...  By extending the learning fashion to semi-supervised learning, we can leverage the massive history data in advertising to enhance the timely updated serving models. • Splitting up federated models: To  ... 
arXiv:2205.15987v1 fatcat:qb6fuhzlbzex3dgdti4igs2n5u

Semi-supervised SVM with Fuzzy Controlled Cooperation of Biology Related Algorithms

Shakhnaz Akhmedova, Eugene Semenkin, Vladimir Stanovov
2017 Proceedings of the 14th International Conference on Informatics in Control, Automation and Robotics  
Due to its wide applicability, the problem of semi-supervised classification is attracting increasing attention in machine learning.  ...  Semi-supervised SVM with Fuzzy Controlled Cooperation of Biology Related Algorithms.  ...  ACKNOWLEDGEMENTS Research is performed with the support of the Ministry of Education and Science of Russian Federation within State Assignment project № 2.1680.2017/ПЧ.  ... 
doi:10.5220/0006417400640071 dblp:conf/icinco/AkhmedovaSS17 fatcat:sklii7hkcjbknmj4ielzp44cz4
« Previous Showing results 1 — 15 out of 8,630 results