Filters








3,144 Hits in 9.0 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).  ...  Second, we find that Batch Normalization (BN) increases gradient diversity. Replacing BN with the recently-proposed Group Normalization (GN) can reduce gradient diversity and improve test accuracy.  ...  Our conclusions do not necessarily reflect the position or the policy of our sponsors, and no official endorsement should be inferred.  ... 
arXiv:2008.11364v2 fatcat:ixy7htug7favtl6pjhogualbxa

Federated Domain Adaptation for ASR with Full Self-Supervision [article]

Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli, Frank Seide
2022 arXiv   pre-print
Cross-device federated learning (FL) protects user privacy by collaboratively training a model on user devices, therefore eliminating the need for collecting, storing, and manually labeling user data.  ...  The system can improve a strong Emformer-Transducer based ASR model pretrained on out-of-domain data, using in-domain audio without any ground-truth transcriptions.  ...  Confidence filtering and data augmentation are used to improve the semi-supervised learning performance.  ... 
arXiv:2203.15966v2 fatcat:4d6nnpj445bvzbffrpwlldwmum

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.  ...  Semi-FedSER When the label rate of the local client is at 20%, we can observe that the SER performance of the federated supervised model drops 5-10% compared to the fully federated supervised model on  ... 
arXiv:2203.08810v1 fatcat:vg7shrkgcrht7lfxnbknc6qx54

FedCon: A Contrastive Framework for Federated Semi-Supervised Learning [article]

Zewei Long, Jiaqi Wang, Yaqing Wang, Houping Xiao, Fenglong Ma
2021 arXiv   pre-print
Federated Semi-Supervised Learning (FedSSL) has gained rising attention from both academic and industrial researchers, due to its unique characteristics of co-training machine learning models with isolated  ...  Besides, ablation studies demonstrate the characteristics of the proposed FedCon framework.  ...  Federated semi-supervised learning (FedSSL), which introduces unlabeled data into federated learning, significantly increases the difficulty of the analysis of model training.  ... 
arXiv:2109.04533v1 fatcat:nwq23fs4nzbcpefptg3xlvq7mu

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.  ...  Notably, we show that with as little as 3% labeled data available, FedSTAR on average can improve the recognition rate by 13.28% compared to the fully supervised federated model.  ...  Through extensive evaluation, we demonstrate that the convergence rate of our proposed semi-supervised federated algorithm, i.e., FedSTAR, can be greatly improved by using a pre-trained model learned in  ... 
arXiv:2107.06877v2 fatcat:hf3dr6i3n5c5bmzjkm6f2y3kei

Federated Semi-Supervised Learning with Prototypical Networks [article]

Woojung Kim, Keondo Park, Kihyuk Sohn, Raphael Shu, Hyung-Sin Kim
2022 arXiv   pre-print
With the increasing computing power of edge devices, Federated Learning (FL) emerges to enable model training without privacy concerns.  ...  Recently, federated semi-supervised learning (FSSL) is explored as a way to effectively utilize unlabeled data during training.  ...  Federated Semi-Supervised Learning (FSSL).  ... 
arXiv:2205.13921v2 fatcat:j6hkgry6dfa25dwd3x245fthnm

Poisoning Semi-supervised Federated Learning via Unlabeled Data: Attacks and Defenses [article]

Yi Liu, Xingliang Yuan, Ruihui Zhao, Cong Wang, Dusit Niyato, Yefeng Zheng
2022 arXiv   pre-print
Our attack utilizes the natural characteristic of semi-supervised learning to cause the model to be poisoned by poisoning unlabeled data.  ...  Semi-supervised Federated Learning (SSFL) has recently drawn much attention due to its practical consideration, i.e., the clients may only have unlabeled data.  ...  Semi-supervised Federated Learning We first review the limitations of supervised federated learning (SFL).  ... 
arXiv:2012.04432v2 fatcat:3wxbf2twhfcopenn2u3shyffoi

Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning [article]

Shaoxiong Ji and Teemu Saravirta and Shirui Pan and Guodong Long and Anwar Walid
2021 arXiv   pre-print
Specifically, we explore various learning algorithms to improve the vanilla federated averaging algorithm and review model fusion methods such as adaptive aggregation, regularization, clustered methods  ...  We conduct a focused survey of federated learning in conjunction with other learning algorithms.  ...  Our paper fills in its gap by including a wider range of model fusion and learning algorithms. [54] Semi-supervised learning Xu et al. [50] Healthcare informatics Lo et al.  ... 
arXiv:2102.12920v2 fatcat:5fcwfhxibbedbcbuzrfyqdedky

FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation [article]

Jeffry Wicaksana, Zengqiang Yan, Dong Zhang, Xijie Huang, Huimin Wu, Xin Yang, Kwang-Ting Cheng
2022 arXiv   pre-print
The purpose of federated learning is to enable multiple clients to jointly train a machine learning model without sharing data.  ...  In FedMix, each client updates the federated model by integrating and effectively making use of all available labeled data ranging from strong pixel-level labels, weak bounding box labels, to weakest image-level  ...  Semi-supervised Federated Learning In a standard federated learning setting, not every local client has access to pixel-level supervision for image segmentation to facilitate model learning with weakly-labeled  ... 
arXiv:2205.01840v1 fatcat:zlxyuakbfrbpbiv5cid6czvqzu

Fed-Sim: Federated Simulation for Medical Imaging [article]

Daiqing Li, Amlan Kar, Nishant Ravikumar, Alejandro F Frangi, Sanja Fidler
2020 arXiv   pre-print
Since the model of geometry and material is disentangled from the imaging sensor, it can effectively be trained across multiple medical centers.  ...  Exploiting a larger pool of labeled data available across multiple centers, such as in federated learning, has also seen limited success since current deep learning approaches do not generalize well to  ...  Semi-Supervised Learning: We utilize the unlabelled data (which is typically more widely available) in the training set to improve our simulation.  ... 
arXiv:2009.00668v1 fatcat:jndsdd2pkvfznmafkh6tyt7qoy

FedSiam: Towards Adaptive Federated Semi-Supervised Learning [article]

Zewei Long, Liwei Che, Yaqing Wang, Muchao Ye, Junyu Luo, Jinze Wu, Houping Xiao, Fenglong Ma
2021 arXiv   pre-print
In this paper, we focus on designing a general framework FedSiam to tackle different scenarios of federated semi-supervised learning, including four settings in the labels-at-client scenario and two setting  ...  Federated learning (FL) has emerged as an effective technique to co-training machine learning models without actually sharing data and leaking privacy.  ...  Similar to standard federated semi-supervised learning in the parameter aggregation step, we can obtain using the average of selected local models by Eq. (2).  ... 
arXiv:2012.03292v2 fatcat:bmurr4mrpzbrrkpqww6jtpzs6a

Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging [article]

Rui Yan, Liangqiong Qu, Qingyue Wei, Shih-Cheng Huang, Liyue Shen, Daniel Rubin, Lei Xing, Yuyin Zhou
2022 arXiv   pre-print
by 10.36% and the semi-supervised FL method by 8.3% in test accuracy.  ...  Moreover, we show that our self-supervised FL algorithm generalizes well to out-of-distribution data and learns federated models more effectively in limited label scenarios, surpassing the supervised baseline  ...  In the federated pre-training stage, each local client takes E steps of gradient descent to update the local model E k and D k by minimizing its local loss L k on data D k .  ... 
arXiv:2205.08576v1 fatcat:ktzzyotj6jdq5mtq46vfvw3bmy

Dynamic Gradient Aggregation for Federated Domain Adaptation [article]

Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
2021 arXiv   pre-print
In this paper, a new learning algorithm for Federated Learning (FL) is introduced.  ...  Further, the aggregation algorithm acts as a regularizer of the gradient quality. We investigate the effect of our FL algorithm in supervised and unsupervised Speech Recognition (SR) scenarios.  ...  Semi-supervised Learning with DGA To verify the efficacy of DGA, we ran another set of SR experiments on meeting data in a semi-supervised scenario.  ... 
arXiv:2106.07578v1 fatcat:xgbkwqfxsvas5epyzvrm2q7jrq

Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Design [article]

Zhe Zhang, Shiyao Ma, Jiangtian Nie, Yi Wu, Qiang Yan, Xiaoke Xu, Dusit Niyato
2021 arXiv   pre-print
FedMix improves the naive combination of FL and semi-supervised learning methods and designs parameter decomposition strategies for disjointed learning of labeled, unlabeled data, and global models.  ...  Federated Learning (FL) allows edge devices (or clients) to keep data locally while simultaneously training a shared high-quality global model.  ...  Semi-supervised Federated Learning Semi-supervised federated learning attempts to use semisupervised learning techniques [19] - [23] to further improve the performance of the FL model in scenarios where  ... 
arXiv:2110.13388v1 fatcat:pcz2nvd5c5exlkdliqhm2slara

Federated Transfer Learning with Dynamic Gradient Aggregation [article]

Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
2020 arXiv   pre-print
The proposed Federated Learning system is shown to outperform the golden standard of distributed training in both convergence speed and overall model performance.  ...  In this paper, a Federated Learning (FL) simulation platform is introduced. The target scenario is Acoustic Model training based on this platform.  ...  ACKNOWLEDGEMENTS The authors would like to thank Masaki Itagaki, Ziad Al Bawab, Lei He, Michael Zeng, Xuedong Huang, Veljko Miljanic and Frank Seide for their project support and technical discussions.  ... 
arXiv:2008.02452v1 fatcat:k6t56opr55hftplhiwp7kwigtm
« Previous Showing results 1 — 15 out of 3,144 results