Tootfinder

RobQFL: Robust Quantum Federated Learning in Adversarial Environment
Walid El Maouaki, Nouhaila Innan, Alberto Marchisio, Taoufik Said, Muhammad Shafique, Mohamed Bennai
https://arxiv.org/abs/2509.04914

RobQFL: Robust Quantum Federated Learning in Adversarial Environment
Quantum Federated Learning (QFL) merges privacy-preserving federation with quantum computing gains, yet its resilience to adversarial noise is unknown. We first show that QFL is as fragile as centralized quantum learning. We propose Robust Quantum Federated Learning (RobQFL), embedding adversarial training directly into the federated loop. RobQFL exposes tunable axes: client coverage $γ$ (0-100\%), perturbation scheduling (fixed-$\varepsilon$ vs $\varepsilon$-mixes), and optimization (fine-tun…

Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights
Cosmin-Andrei Hatfaludi, Alex Serban
https://arxiv.org/abs/2509.05142 https://

Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights
Federated learning has the potential to unlock siloed data and distributed resources by enabling collaborative model training without sharing private data. As more complex foundational models gain widespread use, the need to expand training resources and integrate privately owned data grows as well. In this article, we explore the intersection of federated learning and foundational models, aiming to identify, categorize, and characterize technical methods that integrate the two paradigms. As a …

🚨 New SciFi story out by the excellent Pippa Goldschmidt, free and sponsored by the *National Academy of Sciences*
https://issues.org/futuretensefiction/the-way-out-pippa-goldschmidt/

The Way Out | Future Tense Fiction
Can animal behavior predict extreme weather? Pippa Goldschmidt’s story imagines a future in which analysts anticipate climate catastrophes by monitoring bats.

If you're interested in #selfhosting, here's a reminder that there is a new bots that replaced the old a.gup.pe bots. The bots improve message propagation.
@…
For those who don’t know, these bots exist because when you look for a a hashtag, your server only checks the postgs that have been federated to it.
In order for a message to be federated to your server, the author (or one of the people boosting it) have to be followed by someone on your server. If no one touching the message is being followed, it’ll never get federated to your server and you won’t see it.
So yes, hashtags are great, but they don’t help message propagation nearly as much as bots can.

Federated Split Learning for Resource-Constrained Robots in Industrial IoT: Framework Comparison, Optimization Strategies, and Future Directions
Wanli Ni, Hui Tian, Shuai Wang, Chengyang Li, Lei Sun, Zhaohui Yang
https://arxiv.org/abs/2510.05713

Federated Split Learning for Resource-Constrained Robots in Industrial IoT: Framework Comparison, Optimization Strategies, and Future Directions
Federated split learning (FedSL) has emerged as a promising paradigm for enabling collaborative intelligence in industrial Internet of Things (IoT) systems, particularly in smart factories where data privacy, communication efficiency, and device heterogeneity are critical concerns. In this article, we present a comprehensive study of FedSL frameworks tailored for resource-constrained robots in industrial scenarios. We compare synchronous, asynchronous, hierarchical, and heterogeneous FedSL fram…

I think he is trying to say he is an Avenger without realising he is the supervillain.
Also, does he know that while he is torrenting the world libraries into his bank account, you could set up for $10 a month your own Mastodon instance which is ten times better federated than his 'federated' Threads?

Series D, Episode 03 - Traitor
VILA: He's not the man for the job. Tarrant has about as much subtlety as a Tarzian Warg Strangler. All I'm saying is Tarrant's going to walk straight into trouble and get himself killed or captured. If he's dead he can't talk. But if the Federation find out we're hanging around, we won't stand a chance. Not in this ship. At least in the Liberator we could always outrun them.
AVON: Vila, if the Federation do have some ne…

An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data
Jiaojiao Zhang, Yuqi Xu, Kun Yuan
https://arxiv.org/abs/2509.05213 https://arx…

An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data
This work addresses the key challenges of applying federated learning to large-scale deep neural networks, particularly the issue of client drift due to data heterogeneity across clients and the high costs of communication, computation, and memory. We propose FedSub, an efficient subspace algorithm for federated learning on heterogeneous data. Specifically, FedSub utilizes subspace projection to guarantee local updates of each client within low-dimensional subspaces, thereby reducing communicat…

If you're interested in #neurospicy or #neurodivergent, here's a reminder that there are new bots that replaced the old a.gup.pe bots. The bots improve message propagation.
@…
@…
For those who don’t know, these bots exist because when you look for a a hashtag, your server only checks the postgs that have been federated to it.
In order for a message to be federated to your server, the author (or one of the people boosting it) have to be followed by someone on your server. If no one touching the message is being followed, it’ll never get federated to your server and you won’t see it.
So yes, hashtags are great, but they don’t help message propagation.

Federated Computation of ROC and PR Curves
Xuefeng Xu, Graham Cormode
https://arxiv.org/abs/2510.04979 https://arxiv.org/pdf/2510.04979

Federated Computation of ROC and PR Curves
Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves are fundamental tools for evaluating machine learning classifiers, offering detailed insights into the trade-offs between true positive rate vs. false positive rate (ROC) or precision vs. recall (PR). However, in Federated Learning (FL) scenarios, where data is distributed across multiple clients, computing these curves is challenging due to privacy and communication constraints. Specifically, the server cannot access raw …