此外,联邦学习框架往往还会有持续不断的新用户的参与,这些新用户往往有着大量的新数据类别,这样会进一步加剧全局模型的灾难性遗忘。为了应对这些挑战,我们提出了一种全新的全局-局部遗忘补偿 (GLFC) 模型,即同时从global和local两个角度出发,尽可能地减弱灾难性遗忘,使得联邦学习最终可训练一个全局增量模型。
Figure 1: FLUTE’s client-server architecture and workflow. First, the server pushes the initial global model to the clients and sends training information. Then, the clients train their instances of the global model with locally available data. Finally, all clients return the information to the ...
在 Subgraph-level 的联邦学习中也可能很重要,比如根据分散在多个医疗机构的病人网络来协同预测疾病的感染情况。 Generating Federated Learning Datasets 不同于传统的 ML 标记数据集,图数据集和现实世界的图可能会由于结构和特征异质性等来源而表现出 no-IID。在联邦学习背景下,多种来源的 no-IID 无法区分。因此 Fe...
We propose a new optimization formulation for training federated learning models. The standard formulation has the form of an empirical risk minimization problem constructed to find a single global model trained from the private data stored across all participating devices. In contrast, our formulation ...
论文笔记:arXiv'21 A Vertical Federated Learning Framework for Graph Convolutional Network 前言: 受限于数据隐私问题和数据孤岛问题,本文提出 FedVGCN,基于联邦学习的 GCN 学习范式。该框架用于数据纵向分割设置下并考虑隐私保护的节点分类任务,该框架可以推广到现有的 GCN 模型。具体来说将计算过程分成两部分。对于...
Federated Learning of a Mixture of Global and Local ModelsFilip HanzelyPeter Richtarik
Federated learning (FL) is a trending training paradigm to utilize decentralized training data. FL allows clients to update model parameters locally for several epochs, then share them to a global model for aggregation. This training paradigm with multi-local step updating before aggregation exposes ...
4.1. Federated Learning Overview FL is a technique to develop a robust quality shared global model with a central aggregate server from isolated data among many different clients. In a healthcare application scenario, assume there are 𝐾K nodes where each node 𝑘k holds its respective data ...
A survey on federated learning Authors Chen Zhang, Yu Xie, Hang Bai, Bin Yu, Weihong Li, Yuan Gao Keywords Federated learning; Privacy protection; Mac
标题:SecureBoost: A Lossless Federated Learning Framework 作者:Kewei Cheng, Tao Fan, Yilun Jin, Yang Liu, Tianjian Chen, Dimitrios Papadopoulos, Qiang Yang公众号:《差分隐私》 先简单梳理一下本文总的脉络吧,论文结构分为9个章节,如下: 0 摘要 1 介绍 2 背景知识&相关工作 3 问题阐述 4 SecureBoost ...