paper-with-me

홈 › Papers

Weighted Sampled Split Learning (WSSL): Balancing Privacy, Robustness, and Fairness in Distributed Learning Environments

2023-10-27 · Manish Osti, Aashray Thakuri, Basheer Qolomany, Aos Mulahuwaish

This study presents Weighted Sampled Split Learning (WSSL), an innovative framework tailored to bolster privacy, robustness, and fairness in distributed machine learning systems. Unlike traditional approaches, WSSL disperses the learning process among multiple clients, thereby safeguarding data confidentiality. Central to WSSL's efficacy is its utilization of weighted sampling. This approach ensures equitable learning by tactically selecting influential clients based on their contributions. Our evaluation of WSSL spanned various client configurations and employed two distinct datasets: Human Gait Sensor and CIFAR-10. We observed three primary benefits: heightened model accuracy, enhanced robustness, and maintained fairness across diverse client compositions. Notably, our distributed frameworks consistently surpassed centralized counterparts, registering accuracy peaks of 82.63% and 75.51% for the Human Gait Sensor and CIFAR-10 datasets, respectively. These figures contrast with the top accuracies of 81.12% and 58.60% achieved by centralized systems. Collectively, our findings champion WSSL as a potent and scalable successor to conventional centralized learning, marking it as a pivotal stride forward in privacy-focused, resilient, and impartial distributed machine learning.

📄 PDF Abstract BibTeX arXiv:2310.18479

Code (0)

등록된 구현이 없습니다.

Tasks

Fairness

Similar Papers 제목 키워드 기반

WSSL: Weighted Self-supervised Learning Framework For Image-inpainting

2022-11-25 · Shubham Gupta, Rahul Kunigal Ravishankar, Madhoolika Gangaraju, Poojasree Dwarkanath 외

Image inpainting is the process of regenerating lost parts of the image. Supervised algorithm-based methods have shown excellent results but have two significant drawbacks. They do not perform well when tested with unsee…

Image InpaintingSelf-Supervised Learning

Rethinking Open-World Semi-Supervised Learning: Distribution Mismatch and Inductive Inference

2024-05-31 · Seongheon Park, Hyuk Kwon, Kwanghoon Sohn, Kibok Lee

Open-world semi-supervised learning (OWSSL) extends conventional semi-supervised learning to open-world scenarios by taking account of novel categories in unlabeled datasets. Despite the recent advancements in OWSSL, the…

Open-World Semi-Supervised Learning

SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning

2026-04-30 · Hezhao Liu, Jiacheng Yang, Junlong Gao, Mengke Li 외 arxiv

In open-world semi-supervised learning (OWSSL), a model learns from labeled data and unlabeled data containing both known and novel classes. In practical OWSSL applications, models are expected to perform rigorous classi…

Open-World Semi-Supervised LearningSemantic correspondence

Privacy-Preserving Collaborative Split Learning Framework for Smart Grid Load Forecasting

2024-03-03 · Asif Iqbal, Prosanta Gope, Biplab Sikdar

Accurate load forecasting is crucial for energy management, infrastructure planning, and demand-supply balancing. Smart meter data availability has led to the demand for sensor-based load forecasting. Conventional ML all…

energy managementLoad ForecastingPrivacy Preserving

SplitFedZip: Learned Compression for Data Transfer Reduction in Split-Federated Learning

2024-12-18 · Chamani Shiranthika, Hadi Hadizadeh, Parvaneh Saeedi, Ivan V. Bajić

Federated Learning (FL) enables multiple clients to train a collaborative model without sharing their local data. Split Learning (SL) allows a model to be trained in a split manner across different locations. Split-Feder…

Federated LearningImage SegmentationMedical Image SegmentationSemantic Segmentation