Tootfinder

Efficient Training of Large-Scale AI Models Through Federated Mixture-of-Experts: A System-Level Approach
Xiaobing Chen, Boyang Zhang, Xiangwei Zhou, Mingxuan Sun, Shuai Zhang, Songyang Zhang, Geoffrey Ye Li
https://arxiv.org/abs/2507.05685

Efficient Training of Large-Scale AI Models Through Federated Mixture-of-Experts: A System-Level Approach
The integration of Federated Learning (FL) and Mixture-of-Experts (MoE) presents a compelling pathway for training more powerful, large-scale artificial intelligence models (LAMs) on decentralized data while preserving privacy. However, efficient federated training of these complex MoE-structured LAMs is hindered by significant system-level challenges, particularly in managing the interplay between heterogeneous client resources and the sophisticated coordination required for numerous specializ…

The American Federation of Teachers, the US' second-largest teachers' union, plans to start an AI training hub with $23M from Microsoft, OpenAI, and Anthropic (Natasha Singer/New York Times)
https://www.nytimes.com/2025/07/08/technology…

OpenAI and Microsoft Bankroll New A.I. Training for Teachers
The American Federation of Teachers said it would use the $23 million, including $500,000 from the A.I. start-up Anthropic, to create a national training center.

Communication-Efficient Module-Wise Federated Learning for Grasp Pose Detection in Cluttered Environments
Woonsang Kang, Joohyung Lee, Seungjun Kim, Jungchan Cho, Yoonseon Oh
https://arxiv.org/abs/2507.05861

Communication-Efficient Module-Wise Federated Learning for Grasp Pose Detection in Cluttered Environments
Grasp pose detection (GPD) is a fundamental capability for robotic autonomy, but its reliance on large, diverse datasets creates significant data privacy and centralization challenges. Federated Learning (FL) offers a privacy-preserving solution, but its application to GPD is hindered by the substantial communication overhead of large models, a key issue for resource-constrained robots. To address this, we propose a novel module-wise FL framework that begins by analyzing the learning dynamics o…

PROTEAN: Federated Intrusion Detection in Non-IID Environments through Prototype-Based Knowledge Sharing
Sara Chennoufi, Yufei Han, Gregory Blanc, Emiliano De Cristofaro, Christophe Kiennert
https://arxiv.org/abs/2507.05524

PROTEAN: Federated Intrusion Detection in Non-IID Environments through Prototype-Based Knowledge Sharing
In distributed networks, participants often face diverse and fast-evolving cyberattacks. This makes techniques based on Federated Learning (FL) a promising mitigation strategy. By only exchanging model updates, FL participants can collaboratively build detection models without revealing sensitive information, e.g., network structures or security postures. However, the effectiveness of FL solutions is often hindered by significant data heterogeneity, as attack patterns often differ drastically a…

Publishing's class problem
The 2024 data shows a similar picture of middle-class origin dominance of publishing. Although there are year-on-year variations, since 2019 there has consistently been more than 60% proportions of middle-class origin people in publishing occupations. In the same period, working-class origin proportions have never been above 20%.
#FederatedMemory

Some WordPress veterans and the Linux Foundation start FAIR, a federated update network to decentralize WordPress infrastructure and boost supply chain security (Chris Stokel-Walker/Fast Company)
https://www.fastcompany.com/91347003/wordp

WordPress veterans launch FAIR project to tackle security and control concerns
Backed by the Linux Foundation, the new federated update network aims to decentralize WordPress infrastructure, strengthen supply chain security, and restore trust amid growing tensions with Automattic.

Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning
Samuel Ofosu Mensah, Kerol Djoumessi, Philipp Berens
https://arxiv.org/abs/2507.05852

Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning
Federated learning (FL) provides a promising paradigm for collaboratively training machine learning models across distributed data sources while maintaining privacy. Nevertheless, real-world FL often faces major challenges including communication overhead during the transfer of large model parameters and statistical heterogeneity, arising from non-identical independent data distributions across clients. In this work, we propose an FL framework that 1) provides inherent interpretations using pro…

BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning
Thinh Dao, Dung Thuy Nguyen, Khoa D Doan, Kok-Seng Wong
https://arxiv.org/abs/2507.04903

BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning
Federated Learning (FL) systems are vulnerable to backdoor attacks, where adversaries train their local models on poisoned data and submit poisoned model updates to compromise the global model. Despite numerous proposed attacks and defenses, divergent experimental settings, implementation errors, and unrealistic assumptions hinder fair comparisons and valid conclusions about their effectiveness in real-world scenarios. To address this, we introduce BackFed - a comprehensive benchmark suite desi…

Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
Yujia Huo, Jianchun Liu, Hongli Xu, Zhenguo Ma, Shilong Wang, Liusheng Huang
https://arxiv.org/abs/2506.05977

Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
Federated fine-tuning (FedFT) of large language models (LLMs) has emerged as a promising solution for adapting models to distributed data environments while ensuring data privacy. Existing FedFT methods predominantly utilize parameter-efficient fine-tuning (PEFT) techniques to reduce communication and computation overhead. However, they often fail to adequately address the catastrophic forgetting, a critical challenge arising from continual adaptation in distributed environments. The tradit…

FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model
Md Jueal Mia, M. Hadi Amini
https://arxiv.org/abs/2506.05640 https://…

FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model
Federated Learning (FL) offers a decentralized framework for training and fine-tuning Large Language Models (LLMs) by leveraging computational resources across organizations while keeping sensitive data on local devices. It addresses privacy and security concerns while navigating challenges associated with the substantial computational demands of LLMs, which can be prohibitive for small and medium-sized organizations. FL supports the development of task-specific LLMs for cross-silo applications…