English(EN)Client and Training Data Selection for Computationally Efficient Synchronized Federated Learning
Google通过TEE增强联邦学习隐私；新arXiv论文探讨模型合并与效率
作者PulseAugur 编辑部·[16 个来源]·
Google Research开发了一个新的联邦学习系统，通过可信执行环境（TEEs）增强隐私，允许可验证的数据匿名化和更快的训练。该系统已在Gboard中实现，并建立在先前差分隐私和安全聚合工作的基础上。同时，几篇arXiv论文探讨了联邦学习的进展，包括具有预训练权重的模型合并技术、处理非独立同分布数据和动态客户端参与的框架、渐进式分辨率安全聚合、用于效率的潜在信息共享以及用于安全和通信优化的压缩方法。
AI
arXiv:2303.00897v2 Announce Type: replace Abstract: Federated learning is a distributed learning framework that takes full advantage of private data samples kept on edge devices. In real-world federated learning systems, these data samples are often decentralized and Non-Independ…
arXiv cs.LG
TIER_1English(EN)·Seyed Mohammad Azimi-Abarghouyi·
arXiv:2610.00695v1 Announce Type: cross Abstract: Secure aggregation lets a server recover an aggregate of client updates without observing any individual update, but conventional protocols fix the aggregate precision when clients upload. We introduce and formulate a new progress…
arXiv:2610.01126v1 Announce Type: new Abstract: Federated learning (FL) is a communication-efficient distributed learning paradigm. However, client drift remains one of the most critical challenges, hindering the efficient training of a global model. In this study, we propose a n…
arXiv:2410.23660v2 Announce Type: replace Abstract: Federated learning (FL) is a learning paradigm that enables collaborative training of models using decentralized data. Recently, the utilization of pre-trained weight initialization in FL has been demonstrated to effectively imp…
arXiv cs.LG
TIER_1English(EN)·Sachi Shome, William Eiers·
arXiv:2609.40312v1 Announce Type: new Abstract: Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect update geometry. In this work, we instead treat the compressor's response as a se…
arXiv:2610.01620v1 Announce Type: new Abstract: Federated training of foundation models is constrained by client memory and communication costs. LoRA-based methods reduce these costs through low-rank adapters, but their fixed rank budget can limit adaptation. Gradient low-rank op…
arXiv:2609.39250v1 Announce Type: new Abstract: Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by enabling learning without sharing raw data with a cloud server. Straggling clients have been a problem for FL as they introduce del…
arXiv cs.LG
TIER_1English(EN)·Pengfei Li, Mohammad Khalil·
arXiv:2609.39646v1 Announce Type: new Abstract: Federated learning faces severe communication bottlenecks when clients upload high-dimensional model updates. Existing methods often compress these updates uniformly across all layers. This uniform approach ignores the heterogeneous…
Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by enabling learning without sharing raw data with a cloud server. Straggling clients have been a problem for FL as they introduce delays in aggregating the local models and hence, t…
arXiv:2609.36610v1 Announce Type: new Abstract: Agnostic federated learning (AFL) seeks a model that performs reliably across $m$ heterogeneous workers, but communication remains a bottleneck. We improve communication efficiency by reducing the number of synchronization rounds vi…
arXiv:2609.33037v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) lets language models answer questions more accurately by consulting relevant documents. Many valuable collections, such as medical records, cannot be pooled because of privacy rules. Fe…
arXiv cs.LG
TIER_1English(EN)·Leonardo F. Toso, James Anderson, Rafael Pinot, Nirupam Gupta·
arXiv:2609.36660v1 Announce Type: new Abstract: We study federated learning (FL) with adversarial clients, where the goal is to minimize the average loss of the honest (non-adversarial) clients without knowing their identity. Under heterogeneity, a single shared model parameter i…
Agnostic federated learning (AFL) seeks a model that performs reliably across $m$ heterogeneous workers, but communication remains a bottleneck. We improve communication efficiency by reducing the number of synchronization rounds via faster convergence and the communication cost …
arXiv:2610.00693v1 Announce Type: new Abstract: Federated learning (FL) has recently attracted increasing attention in remote sensing (RS) since it enables collaborative model training across decentralized RS image archives without requiring direct access to local data. However, …
<p>Google Research has unveiled a federated learning system that moves gradient computation from phones into attested server-side TEEs. Access policies are published to Sigstore's Rekor log and the binaries are reproducibly buildable, so central differential privacy can be checke…
