6 papers
Importance-Aware Feature Sparsification for Wireless Split Learning
Bumjun Kim, Yoon Huh, Wan Choi
Wireless split learning (SL) reduces on-device computation by offloading upper layers to a server, yet transmitting high-dimensional intermediate features at each iteration remains…
Differential Privacy in Feature Reconstruction Aided Federated Learning for Agent's Semantic Communication Model Update
Yoon Huh, Bumjun Kim, Wan Choi
This paper proposes a differentially private federated learning (FL) framework built upon an FL algorithm with semantic feature reconstruction (FedSFR) for training semantic commun…
Feature Reconstruction Aided Federated Learning for Image Semantic Communication
Yoon Huh, Bumjun Kim, Wan Choi
Research in semantic communication has garnered considerable attention, particularly in the area of image transmission, where joint source-channel coding (JSCC)-based neural networ…
Federated Learning Enhanced by Feature Reconstruction for Semantic Communication Module Updates of Agents
Yoon Huh, Bumjun Kim, Wan Choi
Recent advancements in semantic communication have primarily focused on image transmission, where neural network-based joint source-channel coding modules play a central role. Howe…
Two Stage Wireless Federated LoRA Fine-Tuning with Sparsified Orthogonal Updates
Bumjun Kim, Wan Choi
Federated fine-tuning with low-rank adaptation (LoRA) communicates only two low-rank matrices instead of the full model, but existing methods typically fix the LoRA rank in advance…
Privacy-Enhanced Over-the-Air Federated Learning via Client-Driven Power Balancing
Bumjun Kim, Hyowoon Seo, Wan Choi
This paper introduces a novel privacy-enhanced over-the-air Federated Learning (OTA-FL) framework using client-driven power balancing (CDPB) to address privacy concerns in OTA-FL s…