FedCuraLM: Reliability-Calibrated and Resource-Aware Label Auditing with Small Language Models for Non-IID Federated AIoT
Open Access
Abstract
Federated Artificial Intelligence of Things (AIoT) activity-recognition systems learn from decentralized wearable and smart-home records with potentially incorrect labels, non-IID client distributions, and unequal edge-device resources. Our objective is to improve downstream learning from these labels while limiting harmful corrections and respecting auditing, review, and communication budgets. FedCuraLM addresses this objective by converting sensor records into deterministic Semantic Evidence Cards, obtaining candidate-constrained small language model (SLM) assessments, and calibrating and combining them with task-model, prototype, and temporal evidence. Conflict-aware decisions retain observed labels, apply provisional soft corrections, request trusted review, or quarantine uncertain samples without overwriting annotations. Review-grounded reliability and communication-budgeted multi-prototype exchange support collaboration, while resource-aware scheduling assigns feasible SLM tiers across heterogeneous devices. Extensive evaluation on WISDM-W, WISDM-P, and CASAS using controlled symmetric, semantic-asymmetric, instance-dependent, and temporal-boundary corruption under varying client heterogeneity reveals that FedCuraLM significantly improves downstream performance over recent baselines and improves lower-tail client outcomes, audit precision, selective-correction safety, calibration, and communication efficiency. Edge-device measurements characterize latency, memory, and energy trade-offs. The findings position federated label curation as a semantic, statistical, communication, and systems problem.Keywords
Funding Information
- National Science Foundation, USA (1742224)
This publication has 16 references indexed in Scilit:
- FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels2026
- Tackling Noisy Clients in Federated Learning with End-to-end Label Correction2024
- FedCorr: Multi-Stage Federated Learning for Label Noise Correction2022
- Information Leakage in Embedding Models2020
- Symmetric Cross Entropy for Robust Learning With Noisy Labels2019
- Smartphone and Smartwatch-Based Biometrics Using Activities of Daily LivingIEEE Access, 2019
- Membership Inference Attacks Against Machine Learning Models2017
- A note on maximizing a submodular set function subject to a knapsack constraintOperations Research Letters, 2004
- An analysis of approximations for maximizing submodular set functions—IMathematical Programming, 1978
- VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITYMonthly Weather Review, 1950