Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning

Ahn, Jin-Hyun; Kim, Kyungsang; Koh, Jeongwan; Li, Quanzheng

doi:10.48550/arxiv.2202.00195

Cited by 3 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are not many studies that comprehensively discussed the privacy-preserving AL. Previous studies in [ 2 ] provide privacy preservation using k -anonymity and differential privacy for AL, while the studies in [ 4 , 5 , 9 ] use a combination of FL and AL to achieve privacy preservation in active learning.…”

Section: Related Workmentioning

confidence: 99%

“…Ahn et al proposed two approaches to preserve privacy in active learning: namely, the separated active learning (S-AL) and federated active learning (F-AL) method [ 5 ]. In S-AL, clients independently execute the AL prior to the FL.…”

Section: Related Workmentioning

confidence: 99%

“…In the scheme of Ahn et al [ 5 ], a cross-silo FL consisting of a server and numerous clients is analyzed. The FedSGD [ 3 ] is used for FL updates, where the global model is produced by iterative stochastic gradient descent (SGD).…”

Section: Vulnerability Analysismentioning

confidence: 99%

“…Still, there is a gradient leakage in the scheme. Both Ahn et al [ 5 ] and Ahmed et al [ 9 ] do not have any additional method to the scheme, so there is a gradient leakage in the scheme.…”

Section: Vulnerability Analysismentioning

confidence: 99%

“…The aim of federated active learning scheme proposed in [ 4 , 5 ] is to provide privacy preservation for AL. This technique does not consider the data leakage from prameters, e.g., gradient, which is exchanged between the server and client during FL training to avoid data leakage.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Homomorphic Encryption-Based Federated Privacy Preservation for Deep Active Learning

Kurniawan

Mambo

2022

Entropy

View full text Add to dashboard Cite

Active learning is a technique for maximizing performance of machine learning with minimal labeling effort and letting the machine automatically and adaptively select the most informative data for labeling. Since the labels on records may contain sensitive information, privacy-preserving mechanisms should be integrated into active learning. We propose a privacy-preservation scheme for active learning using homomorphic encryption-based federated learning. Federated learning provides distributed computation from multiple clients, and homomorphic encryption enhances the privacy preservation of user data with a strong security level. The experimental result shows that the proposed homomorphic encryption-based federated learning scheme can preserve privacy in active learning while maintaining model accuracy. Furthermore, we also provide a Deep Leakage Gradient comparison. The proposed scheme has no gradient leakage compared to the related schemes that have more than 74% gradient leakage.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Vulnerability Analysismentioning

confidence: 99%

“…Still, there is a gradient leakage in the scheme. Both Ahn et al [ 5 ] and Ahmed et al [ 9 ] do not have any additional method to the scheme, so there is a gradient leakage in the scheme.…”

Section: Vulnerability Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Homomorphic Encryption-Based Federated Privacy Preservation for Deep Active Learning

Kurniawan

Mambo

2022

Entropy

View full text Add to dashboard Cite

show abstract

College students’ perceptions of AI-based writing learning tools: With a focus on Google Translate, Naver Papago, and Grammarly

Kim¹,

Han²

2021

meeso

View full text Add to dashboard Cite

Image blending aims to combine multiple images seamlessly. It remains challenging for existing 2D-based methods, especially when input images are misaligned due to differences in 3D camera poses and object shapes. To tackle these issues, we propose a 3D-aware blending method using generative Neural Radiance Fields (NeRF), including two key components: 3D-aware alignment and 3D-aware blending. For 3D-aware alignment, we first estimate the camera pose of the reference image with respect to generative NeRFs and then perform 3D local alignment for each part. To further leverage 3D information of the generative NeRF, we propose 3D-aware blending that directly blends images on the NeRF's latent representation space, rather than raw pixel space. Collectively, our method outperforms existing 2D baselines, as validated by extensive quantitative and qualitative evaluations with FFHQ and AFHQ-Cat.

show abstract

A Semi-Federated Active Learning Framework for Unlabeled Online Network Data

Zhou

Sun

et al. 2023

Mathematics

View full text Add to dashboard Cite

Federated Learning (FL) is a newly emerged federated optimization technique for distributed data in a federated network. The participants in FL that train the model locally are classified into client nodes. The server node assumes the responsibility to aggregate local models from client nodes without data moving. In this regard, FL is an ideal solution to protect data privacy at each node of the network. However, the raw data generated on each node are unlabeled, making it impossible for FL to apply these data directly to train a model. The large volume of data annotating work prevents FL from being widely applied in the real world, especially for online scenarios, where the data are generated continuously. Meanwhile, the data generated on different nodes tend to be differently distributed. It has been proved theoretically and experimentally that non-independent and identically distributed (non-IID) data harm the performance of FL. In this article, we design a semi-federated active learning (semi-FAL) framework to tackle the annotation and non-IID problems jointly. More specifically, the server node can provide (i) a pre-trained model to help each client node annotate the local data uniformly and (ii) an estimation of the global gradient to help correct the local gradient. The evaluation results demonstrate our semi-FAL framework can efficiently handle unlabeled online network data and achieves high accuracy and fast convergence.

show abstract

Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning

Cited by 3 publications

References 24 publications

Homomorphic Encryption-Based Federated Privacy Preservation for Deep Active Learning

Homomorphic Encryption-Based Federated Privacy Preservation for Deep Active Learning

College students’ perceptions of AI-based writing learning tools: With a focus on Google Translate, Naver Papago, and Grammarly

A Semi-Federated Active Learning Framework for Unlabeled Online Network Data

Contact Info

Product

Resources

About