·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning37m◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks37m◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts37m◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning37m◆FrontierChallenge: Evaluating Scientific Workflow Completion37m◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier37m◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising37m◆Strangers to Themselves: What Language Models Say About Themselves Is Generic37m◆Omni Interaction Agent Technical Report37m◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification37m◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability37m◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization37m◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding37m◆Tracing Computation Density in LLMs37m◆Cultural Binding Heads in Language Models37m◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training37m◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models37m◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning37m◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection37m◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation37m◆Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning37m◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks37m◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts37m◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning37m◆FrontierChallenge: Evaluating Scientific Workflow Completion37m◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier37m◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising37m◆Strangers to Themselves: What Language Models Say About Themselves Is Generic37m◆Omni Interaction Agent Technical Report37m◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification37m◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability37m◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization37m◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding37m◆Tracing Computation Density in LLMs37m◆Cultural Binding Heads in Language Models37m◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training37m◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models37m◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning37m◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection37m◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation37m◆
News/Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach
arxiv
PublishedJune 25, 2026 at 4:00 AM
▲bullish

Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach

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

arXiv:2606.24237v1 Announce Type: new Abstract: Federated Graph Learning facilitates collaborative graph modeling across distributed clients while preserving data privacy. However, real-world data categories frequently exhibit long-tailed distributions. Such statistical scarcity severely degrades pe

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

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

Discussion
Mentioned models
01
  • 01
    FedEPD
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
03
#federated-learning#graph-modeling#data-privacy

No replies yet. Be first.

Mentioned models
01
  • 01
    FedEPD
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
03
#federated-learning#graph-modeling#data-privacy

Related coverage

More from ARXIV
arxivBringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning37marxivSubagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks37marxivDistribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts37marxivIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning37m
The Bubble Brief
WEEKLY

Read federated-learning insights every Tuesday — top movers, new releases, story of the week.

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

Originally published on arxiv ↗
HomeModelsNews