#data-heterogeneity News & Analysis

4 articles tagged with #data-heterogeneity. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBullisharXiv – CS AI · Jun 237/10

🧠

Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models

Researchers introduce GLAM (Grounded Latent-Action World Models), a machine learning framework that learns unified action representations across heterogeneous data sources with different action spaces and missing labels. The approach achieves 48% average improvement in task success rates for robotic manipulation tasks by grounding latent actions in environmental prediction rather than relying on hand-engineered alignment techniques.

AINeutralarXiv – CS AI · Jun 106/10

🧠

From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning

A comprehensive survey analyzes federated learning through a data-centric lens, examining how non-IID data heterogeneity, experimental splitting protocols, and adversarial vulnerabilities affect model convergence and stability. The research ranks data properties by their convergence impact and provides actionable guidance for practitioners designing FL systems with predictable performance.

AINeutralarXiv – CS AI · Apr 206/10

🧠

Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning

Researchers propose FedTSP, a federated learning method that uses pre-trained language models to generate semantically-enriched prototypes for improving model performance across heterogeneous data. The approach leverages textual descriptions of classes to preserve semantic relationships while mitigating data heterogeneity challenges in federated settings.

AINeutralarXiv – CS AI · Mar 174/10

🧠

FedPBS: Proximal-Balanced Scaling Federated Learning Model for Robust Personalized Training for Non-IID Data

Researchers propose FedPBS, a new federated learning algorithm that addresses key challenges in distributed AI training including statistical heterogeneity and uneven client participation. The algorithm dynamically adapts batch sizes and applies proximal corrections to improve model convergence while preserving data privacy across distributed clients.