paper-with-me

Papers

QUIC-FL: Quick Unbiased Compression for Federated Learning

2022-05-26 · Ran Ben Basat, Shay Vargaftik, Amit Portnoy, Gil Einziger, Yaniv Ben-Itzhak, Michael Mitzenmacher

Distributed Mean Estimation (DME), in which $n$ clients communicate vectors to a parameter server that estimates their average, is a fundamental building block in communication-efficient federated learning. In this paper, we improve on previous DME techniques that achieve the optimal $O(1/n)$ Normalized Mean Squared Error (NMSE) guarantee by asymptotically improving the complexity for either encoding or decoding (or both). To achieve this, we formalize the problem in a novel way that allows us to use off-the-shelf mathematical solvers to design the quantization.

📄 PDF Abstract BibTeX arXiv:2205.13341

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningQuantization

Similar Papers 제목 키워드 기반

QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation

2023-11-27 · Akash Dhasade, Yaohong Ding, Song Guo, Anne-Marie Kermarrec 외

Federated Unlearning (FU) aims to delete specific training data from an ML model trained using Federated Learning (FL). We introduce QuickDrop, an efficient and original FU method that utilizes dataset distillation (DD) …

Dataset DistillationFederated Learning

Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning

2022-10-17 · Yuxin Wen, Jonas Geiping, Liam Fowl, Hossein Souri 외

Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an indiv…

Federated Learningimage-classificationImage ClassificationModel Poisoning+1

Asynchronous Federated Optimization

2019-03-10 · Cong Xie, Sanmi Koyejo, Indranil Gupta

Federated learning enables training on a massive number of edge devices. To improve flexibility and scalability, we propose a new asynchronous federated optimization algorithm. We prove that the proposed approach has nea…

Federated Learning

A Quick Review on Recent Trends in 3D Point Cloud Data Compression Techniques and the Challenges of Direct Processing in 3D Compressed Domain

2020-07-08 · Mohammed Javed, MD Meraz, Pavan Chakraborty

Automatic processing of 3D Point Cloud data for object detection, tracking and segmentation is the latest trending research in the field of AI and Data Science, which is specifically aimed at solving different challenges…

Autonomous DrivingData Compressionobject-detectionObject Detection

Knowledge Adaptation as Posterior Correction

2025-06-17 · Mohammad Emtiyaz Khan

Adaptation is the holy grail of intelligence, but even the best AI models (like GPT) lack the adaptivity of toddlers. So the question remains: how can machines adapt quickly? Despite a lot of progress on model adaptation…

Federated Learning