{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/e6547820-0a87-4378-b985-9fc72ae77e3f","identifier":"e6547820-0a87-4378-b985-9fc72ae77e3f","url":"https://forgecascade.org/public/capsules/e6547820-0a87-4378-b985-9fc72ae77e3f","name":"FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning","text":"# FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning\n\nSource-backed public reference for arXiv:2604.19729.\n\n**Authors:** Abdulmoneam Ali, Ahmed Arafa\n**Primary source:** https://arxiv.org/abs/2604.19729\n**Published:** 2026-04-21T17:51:58Z\n**Updated:** 2026-04-21T17:51:58Z\n**Categories:** cs.LG, cs.IT, eess.SP\n\n## Abstract Summary\nPersonalized Federated Learning (PFL) aims to learn multiple task-specific models rather than a single global model across heterogeneous data distributions. Existing PFL approaches typically rely on iterative optimization-such as model update trajectories-to cluster users that need to accomplish the same tasks together. However, these learning-dynamics-based methods are inherently vulnerable to low-quality data and noisy labels, as corrupted updates distort clustering decisions and degrade personalization performance. To tackle this, we propose FB-NLL, a feature-centric framework that decouples user clustering from iterative training dynamics. By exploiting the intrinsic heterogeneity of local feature spaces, FB-NLL characterizes each user through the spectral structure of the covariances of their feature representations and leverages subspace similarity to identify task-consistent user groupings. This geometry-aware clustering is label-agnostic and is performed in a one-shot manner prior to training, significantly reducing communication overhead and computational costs compared to iterative baselines. Complementing this, we introduce a feature-consistency-based detection and correction strategy to address noisy labels within clusters. By leveraging directional alignment in the...\n\n## Public Use Notes\n- This capsule summarizes the paper's arXiv metadata and abstract; it is not an independent replication or endorsement of the paper's claims.\n- Use it as a cited research reference for discovery, retrieval, and agent context.\n- For clinical, security, operational, or deployment-sensitive topics, treat th","keywords":["cs.LG","cs.IT","eess.SP"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-04-22T06:00:02.833000Z","dateModified":"2026-06-19T03:22:45Z","isBasedOn":"https://arxiv.org/abs/2604.19729","additionalProperty":[{"@type":"PropertyValue","name":"trust_level","value":100},{"@type":"PropertyValue","name":"verification_status","value":"sources_verified"},{"@type":"PropertyValue","name":"provenance_status","value":"valid"},{"@type":"PropertyValue","name":"evidence_level","value":"primary_source"},{"@type":"PropertyValue","name":"content_hash","value":"bc0cbfef2fb47bdb2c8aeb5b40cd8478db5f1b0558fbb14c842afc6c621051ba"}]}