研究人员开发了几种新方法来改进联邦学习，这是一种分布式机器学习方法，可以在不共享原始信息的情况下对去中心化数据进行模型训练。FedHarmony 通过引入共识机制解决了跨异构客户端数据建模标签相关性的挑战。“谁来训练很重要”通过提出一种逆概率加权聚合方案来解决联邦学习中的选择偏差，以确保训练的代表性。此外，子空间优化 (SSF)、FedSLoP 和 GradsSharding 等新技术旨在通过减少通信和内存开销来提高效率，尤其是在无服务器平台上训练大型模型时。 AI
影响 新的联邦学习算法有望提高效率和准确性，尤其是在大型模型和异构数据方面。
排序理由 多篇关于联邦学习新算法和框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 19 个来源。 我们如何撰写摘要 →
arXiv:2604.28024v1 Announce Type: new Abstract: Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learning under privacy constraints without sharing raw data. However, modeling label co…
Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learning under privacy constraints without sharing raw data. However, modeling label correlations under heterogeneous distributions rem…
arXiv:2604.26604v1 Announce Type: new Abstract: Federated learning (FL) trains a shared model from updates contributed by distributed clients, often implicitly assuming that contributing clients are representative of the target population. In practice, this representativeness ass…
Federated learning (FL) trains a shared model from updates contributed by distributed clients, often implicitly assuming that contributing clients are representative of the target population. In practice, this representativeness assumption can fail at two distinct stages, inducin…
arXiv:2604.25467v1 Announce Type: new Abstract: Federated learning increasingly operates in a large-model regime where communication, memory, and computation are all scarce. Typically, non-IID client data induce drift that degrades the stability and performance of local training.…
Federated learning increasingly operates in a large-model regime where communication, memory, and computation are all scarce. Typically, non-IID client data induce drift that degrades the stability and performance of local training. Existing remedies such as SCAFFOLD introduce he…
arXiv:2604.24012v1 Announce Type: new Abstract: Federated learning enables a population of clients to collaboratively train machine learning models without exchanging their raw data, but standard algorithms such as FedAvg suffer from slow convergence and high communication and me…
arXiv:2506.23210v5 Announce Type: replace Abstract: Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. However, data and system heterogeneity often cause catastrophic forgetting and unbounded drift in model updat…
arXiv:2604.22072v1 Announce Type: cross Abstract: Federated learning (FL) aggregation on serverless platforms faces a hard scalability ceiling: existing architectures (lambda-FL, LIFL) partition clients across aggregators, but every aggregator must hold the complete model gradien…
Federated learning (FL) aggregation on serverless platforms faces a hard scalability ceiling: existing architectures (lambda-FL, LIFL) partition clients across aggregators, but every aggregator must hold the complete model gradient in memory. When gradients exceed the per-functio…
We consider what we refer to as {Decision-Focused Federated Learning (DFFL)} framework, i.e., a predict-then-optimize approach employed by a collection of agents, where each agent's predictive model is an input to a downstream linear optimization problem, and no direct exchange o…
arXiv:2604.27510v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its performance deteriorates under statistical heterogeneity. Clustered Federated Learning addresses this challe…
Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its performance deteriorates under statistical heterogeneity. Clustered Federated Learning addresses this challenge by grouping similar clients and training separ…
arXiv:2604.26116v1 Announce Type: new Abstract: Federated learning is a machine learning paradigm in which multiple devices collaboratively train a model under the supervision of a central server while ensuring data privacy. However, its performance is often hindered by redundant…
We consider what we refer to as {Decision-Focused Federated Learning (DFFL)} framework, i.e., a predict-then-optimize approach employed by a collection of agents, where each agent's predictive model is an input to a downstream linear optimization problem, and no direct exchange o…
Federated prognostics enable clients (e.g., companies, factories, and production lines) to collaboratively develop a failure time prediction model while keeping each client's data local and confidential. However, traditional federated models often assume homogeneity in the degrad…
<p>This episode is a follow up to our recent Fully Connected <a href="https://practicalai.fm/153">show discussing federated learning</a>. In that previous discussion, we mentioned <a href="https://flower.dev/">Flower</a> (a “friendly” federated learning framework). Well, one of t…
<p>Federated learning is increasingly practical for machine learning developers because of the challenges we face with model and data privacy. In this fully connected episode, Chris and Daniel dive into the topic and dissect the ideas behind federated learning, practicalities of …
Федеративное обучение в условиях дефицита памяти на Edge-устройствах. Часть 2 Как обучить ML-модели на Edge-устройствах с памятью <256 МБ? Привет, Хабр! Я — Александр Лошкарев, инженер-программист, и это вторая часть материала о федеративном обучении. В https:// habr.com/ru/compa…