{"id":2126,"date":"2025-11-30T07:38:49","date_gmt":"2025-11-30T07:38:49","guid":{"rendered":"https:\/\/scipapermill.com\/index.php\/2025\/11\/30\/federated-learning-charting-the-course-for-trust-efficiency-and-intelligence-at-the-edge\/"},"modified":"2025-12-28T21:08:54","modified_gmt":"2025-12-28T21:08:54","slug":"federated-learning-charting-the-course-for-trust-efficiency-and-intelligence-at-the-edge","status":"publish","type":"post","link":"https:\/\/scipapermill.com\/index.php\/2025\/11\/30\/federated-learning-charting-the-course-for-trust-efficiency-and-intelligence-at-the-edge\/","title":{"rendered":"Federated Learning: Charting the Course for Trust, Efficiency, and Intelligence at the Edge"},"content":{"rendered":"

Latest 50 papers on federated learning: Nov. 30, 2025<\/h3>\n

Federated Learning (FL) continues to be a pivotal paradigm shift in AI\/ML, promising a future where models learn collaboratively without compromising user data privacy. Yet, this promise comes with a unique set of challenges\u2014from data heterogeneity and communication bottlenecks to robust security against adversarial attacks. Recent research is pushing the boundaries, unveiling innovative solutions that tackle these hurdles head-on, paving the way for FL\u2019s ubiquitous deployment across diverse and sensitive domains.<\/p>\n

The Big Idea(s) & Core Innovations<\/h3>\n

At the heart of recent FL advancements lies a concerted effort to balance privacy, performance, and practical deployability. A key theme emerging is the personalization of federated models<\/em> to better handle diverse client data. For instance, Factor-Assisted Federated Learning for Personalized Optimization with Heterogeneous Data<\/a> by Feifei Wang, Huiyun Tang, and Yang Li<\/strong> from Renmin University of China introduces FedSplit. This framework uses factor analysis (FedFac) to decompose neural network hidden elements into shared and personalized components, significantly improving prediction and convergence in heterogeneous environments. Similarly, Personalized Federated Segmentation with Shared Feature Aggregation and Boundary-Focused Calibration<\/a> from Islamic University of Technology proposes FedOAP, leveraging decoupled cross-attention and boundary-aware loss for organ-agnostic tumor segmentation, ensuring privacy while benefiting from shared features.<\/p>\n

Another critical area is bolstering security and trustworthiness<\/em>. Backdoor attacks remain a formidable threat, and a pioneering work, Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning<\/a> by Chibueze Peace Obioma<\/strong>, introduces FeRA. This defense mechanism uses multi-dimensional behavioral analysis to detect malicious clients, outperforming existing methods. Complementing this, BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning<\/a> by Thinh Dao et al.<\/strong> (VinUni-Illinois Smart Health Center) provides a much-needed standardized benchmark, exposing limitations in current attack and defense evaluations. Furthermore, Privacy-Preserving Federated Vision Transformer Learning Leveraging Lightweight Homomorphic Encryption in Medical AI<\/a> showcases how lightweight homomorphic encryption can secure vision transformers for medical imaging, a critical step for sensitive applications.<\/p>\n

Efficiency in communication and computation is also paramount. ADF-LoRA: Alternating Low-Rank Aggregation for Decentralized Federated Fine-Tuning<\/a> by Fan et al.<\/strong> (Tsinghua University, University of Science and Technology of China) leverages alternating low-rank adaptation (LoRA) to improve decentralized federated fine-tuning of large language models (LLMs) under heterogeneous constraints. This is further explored in ILoRA: Federated Learning with Low-Rank Adaptation for Heterogeneous Client Aggregation<\/a> by Junchao Zhou et al.<\/strong> (Tianjin University), which introduces QR-based initialization and aggregation to stabilize convergence with heterogeneous LoRA ranks. The survey Federated Large Language Models: Current Progress and Future Directions<\/a> by Yuhang Yao et al.<\/strong> (Carnegie Mellon University, Duke University) thoroughly reviews techniques like LoRA for efficient FedLLM training.<\/p>\n

Addressing practical challenges like asynchronicity and dynamic participation<\/em>, Stragglers Can Contribute More: Uncertainty-Aware Distillation for Asynchronous Federated Learning<\/a> by Yujia Wang et al.<\/strong> (Pennsylvania State University) introduces FedEcho. This framework uses uncertainty-aware distillation to intelligently incorporate contributions from \u2018straggler\u2019 clients without directly merging outdated parameters. Meanwhile, Mitigating Participation Imbalance Bias in Asynchronous Federated Learning<\/a> by Xiangyu Chang et al.<\/strong> (University of California, Riverside) proposes ACE and its delay-aware variant ACED, ensuring all clients contribute equally, thereby eliminating participation bias.<\/p>\n

Under the Hood: Models, Datasets, & Benchmarks<\/h3>\n

These innovations are often driven by, or lead to, the development of specialized models, datasets, and benchmarking tools:<\/p>\n