Tootfinder

#caturday https://www.boredpanda.com/cute-funny-cats-pics/?cexp_id=137699&cexp_var=18&_f=homepage_featured

80 Hilarious And Weird Cats To Bless Your Day
They’ve clawed their way into our screens, hearts and possibly even our furniture. Cats the unofficial rulers of the digital world. And we wouldn’t be surprised if they’re secretly plotting to take over the real world too. These feisty felines have been serving looks, chaos and unexpected comedy for centuries. You don’t have to be […]

Federation problems is just something we have to live with in the Fediverse.
Federating has its pros and cons.
I'm Swiss. We know these things.
#switzerland #fediverse #justswissthings

🌐 eduGAIN piloting use of OpenID Federation
eduGAIN has relied on SAML for years, but modern protocols like OpenID Connect 1.0 & OAuth 2.0 are now industry standards.
The eduGAIN service is running a 12-month pilot to test how OpenID Federation could be used as the future trust technology for eduGAIN, alongside SAML.
🔗 Read more in the latest #CONNECT50 article by Lars Fugl…

Adaptive Client Selection via Q-Learning-based Whittle Index in Wireless Federated Learning
Qiyue Li, Yingxin Liu, Hang Qi, Jieping Luo, Zhizhang Liu, Jingjin Wu
https://arxiv.org/abs/2509.13933

Adaptive Client Selection via Q-Learning-based Whittle Index in Wireless Federated Learning
We consider the client selection problem in wireless Federated Learning (FL), with the objective of reducing the total required time to achieve a certain level of learning accuracy. Since the server cannot observe the clients' dynamic states that can change their computation and communication efficiency, we formulate client selection as a restless multi-armed bandit problem. We propose a scalable and efficient approach called the Whittle Index Learning in Federated Q-learning (WILF-Q), which us…

Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Response
Ozer Ozturk, Busra Buyuktanir, Gozde Karatas Baydogmus, Kazim Yildiz
https://arxiv.org/abs/2509.13987

Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Response
Machine learning models used for distributed architectures consisting of servers and clients require large amounts of data to achieve high accuracy. Data obtained from clients are collected on a central server for model training. However, storing data on a central server raises concerns about security and privacy. To address this issue, a federated learning architecture has been proposed. In federated learning, each client trains a local model using its own data. The trained models are periodic…

That’s some free speech right there. #uspol

"This channel has my own videos that I made myself. I used to use Windows but now I use Linux and have made some videos about this. I also have my own blog Andrea Sites."
-- Andrea Borman
https://www.youtube.com/@AndreaBorman/featured

🇺🇦 #NowPlaying on KEXP's #VarietyMix
Seltav:
🎵 SPQR
#Seltav
https://futuretimes.bandcamp.com/track/seltav-spqr

ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learning
Zihou Wu (School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China), Yuecheng Li (School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China), Tianchi Liao (School of Software Engineering, Sun Yat-sen University, Zhuhai, China), Jian Lou (School of Software Engineering, Sun Yat-sen University, Zhuhai, China), Chuan Chen (School of Computer Science and E…

ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learning
Federated learning (FL) faces a critical dilemma: existing protection mechanisms like differential privacy (DP) and homomorphic encryption (HE) enforce a rigid trade-off, forcing a choice between model utility and computational efficiency. This lack of flexibility hinders the practical implementation. To address this, we introduce ParaAegis, a parallel protection framework designed to give practitioners flexible control over the privacy-utility-efficiency balance. Our core innovation is a strat…

FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learning
Zhanting Zhou, Jinshan Lai, Fengchun Zhang, Zeqin Wu, Fengli Zhang
https://arxiv.org/abs/2509.13895

FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learning
Non-IID data and partial participation induce client drift and inconsistent local optima in federated learning, causing unstable convergence and accuracy loss. We present FedSSG, a stochastic sampling-guided, history-aware drift alignment method. FedSSG maintains a per-client drift memory that accumulates local model differences as a lightweight sketch of historical gradients; crucially, it gates both the memory update and the local alignment term by a smooth function of the observed/expected p…