arXiv:2401.09986v3 Announce Type: replace-cross
Abstract: Federated learning is inherently hampered by data heterogeneity: non-i.i.d. training data over local clients. We propose a novel model training approach for federated learning, FLex&Chill, which exploits the Logit Chilling method. Through extensive evaluations, we demonstrate that, in the presence of non-i.i.d. data characteristics inherent in federated learning systems, this approach can expedite model convergence and improve inference accuracy. Quantitatively, from our experiments, we observe up to 6X improvement in the global federated learning model convergence time, and up to 3.37% improvement in inference accuracy.
Multi-LLM Thematic Analysis with Dual Reliability Metrics: Combining Cohen’s Kappa and Semantic Similarity for Qualitative Research Validation
arXiv:2512.20352v1 Announce Type: cross Abstract: Qualitative research faces a critical reliability challenge: traditional inter-rater agreement methods require multiple human coders, are time-intensive, and often yield