·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Anthropic’s cloud partnerships are getting messy1h◆SpaceX’s AI business is beating expectations2h◆OpenAI acquires startup Orchestra Bio⁠ to beef up its biotech business2h◆Google has joined Amazon in attacking Nvidia’s stronghold with AI app developers4h◆ChatGPT now lets you lock your chats4h◆NVIDIA Cosmos3-H-Dreams: Bringing Clinical Surgery to Life Through Generative Simulation4h◆Meta pauses Muse sharing after researchers find AI chats on the web4h◆Eric Schmidt reportedly owns about half as much of Anthropic as CEO Dario Amodei5h◆Meta’s Muse hits 10M U.S. downloads in 40 days, a milestone reached by only 11 other apps5h◆FairStress: A deeper evaluation of fairness in LLM decision-making6h◆Plants can speak using electricity, so this startup built an AI model to decipher their language7h◆The new economics of enterprise AI7h◆ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model7h◆Spotify pulled 50 million AI slop and spam tracks from its recommendations8h◆Figma co-founder Dylan Field thinks MCP is not a perfect protocol8h◆US orders federal agencies to remove China’s DeepSeek AI from their systems9h◆Adobe Lightroom mobile can now open closed eyes in photos with a simple tap9h◆Eka is worth $1.45B thanks to a physical AI model that has experts raving10h◆AI adoption by industry shows what other sectors can learn11h◆Otter.ai raises $320 million from General Catalyst’s growth fund for its meeting tool12h◆Anthropic’s cloud partnerships are getting messy1h◆SpaceX’s AI business is beating expectations2h◆OpenAI acquires startup Orchestra Bio⁠ to beef up its biotech business2h◆Google has joined Amazon in attacking Nvidia’s stronghold with AI app developers4h◆ChatGPT now lets you lock your chats4h◆NVIDIA Cosmos3-H-Dreams: Bringing Clinical Surgery to Life Through Generative Simulation4h◆Meta pauses Muse sharing after researchers find AI chats on the web4h◆Eric Schmidt reportedly owns about half as much of Anthropic as CEO Dario Amodei5h◆Meta’s Muse hits 10M U.S. downloads in 40 days, a milestone reached by only 11 other apps5h◆FairStress: A deeper evaluation of fairness in LLM decision-making6h◆Plants can speak using electricity, so this startup built an AI model to decipher their language7h◆The new economics of enterprise AI7h◆ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model7h◆Spotify pulled 50 million AI slop and spam tracks from its recommendations8h◆Figma co-founder Dylan Field thinks MCP is not a perfect protocol8h◆US orders federal agencies to remove China’s DeepSeek AI from their systems9h◆Adobe Lightroom mobile can now open closed eyes in photos with a simple tap9h◆Eka is worth $1.45B thanks to a physical AI model that has experts raving10h◆AI adoption by industry shows what other sectors can learn11h◆Otter.ai raises $320 million from General Catalyst’s growth fund for its meeting tool12h◆
News/Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning
arxiv
PublishedApril 22, 2026 at 4:00 AM
▲bullish

Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2602.12708v2 Announce Type: replace Abstract: Vertical Federated Learning (VFL) has emerged as a critical paradigm for collaborative model training in privacy-sensitive domains such as finance and healthcare. However, most existing VFL frameworks rely on the idealized assumption of full sample

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Mentioned models
05
  • 01
    Split-MoPE
  • 02
    LASER
  • 03
    Vertical SplitNN
  • 04
    Mixture of Experts (MoE)
  • 05
    Mixture of Predefined Experts (MoPE)
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#federated-learning#collaborative-model-training#privacy-sensitive-domains#split-learning

No replies yet. Be first.

Mentioned models
05
  • 01
    Split-MoPE
  • 02
    LASER
  • 03
    Vertical SplitNN
  • 04
    Mixture of Experts (MoE)
  • 05
    Mixture of Predefined Experts (MoPE)
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#federated-learning#collaborative-model-training#privacy-sensitive-domains#split-learning
The Bubble Brief
MON · WED · FRI

Read federated-learning insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews