Adaptive Client Selection for Efficient Federated Code Generation Under Data Skew

This report synthesises findings from 8 peer-reviewed papers addressing the following research question: Does adaptive client selection improve the inference efficiency and final accuracy of code generation models in federated settings compared to random sampling strategies under high data skew. Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called. 12 claims were extracted from source literature; 12 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Does adaptive client selection improve the inference efficiency and final accuracy of code generation models in federated settings compared to random sampling strategies under high data skew?

Autonomous literature synthesis. Automated review score: 9.2/10. Full text and citation available at Assignee Research.