Fast converging Federated Learning with Non-IID Data

Si Ahmed Naas*, Stephan Sigg

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

22 Lataukset (Pure)


With the advancement of device capabilities, Internet of Things (IoT) devices can employ built-in hardware to perform machine learning (ML) tasks, extending their horizons in many promising directions. In traditional ML, data are sent to a server for training. However, this approach raises user privacy concerns. On the other hand, transferring user data to a cloud-centric environment results in increased latency. A decentralized ML technique, Federated learning (FL), has been proposed to enable devices to train locally on personal data and then send the data to a server for model aggregation. In these models, malicious devices, or devices with a minor contribution to a global model, increase communication rounds and resource usage. Likewise, heterogeneous data, such as non-independent and identically distributed (Non-IID), may decrease accuracy of the FL model. This paper proposes a mechanism to quantify device contributions based on weight divergence. We propose an outlier-removal approach which identifies irrelevant device updates. Client selection probabilities are computed using a Bayesian model. To obtain a global model, we employ a novel merging algorithm utilizing weight shifting values to ensure convergence towards more accurate predictions. A simulation using the MNIST dataset employing both non-iid and iid devices, distributed on 10 Jetson Nano devices, shows that our approach converges faster, significantly reduces communication cost, and improves accuracy.

Otsikko2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings
ISBN (elektroninen)979-8-3503-1114-3
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE Vehicular Technology Conference - Florence, Italy, Florence, Italia
Kesto: 20 kesäk. 202323 kesäk. 2023
Konferenssinumero: 97


NimiIEEE Vehicular Technology Conference
ISSN (painettu)1550-2252


ConferenceIEEE Vehicular Technology Conference


Sukella tutkimusaiheisiin 'Fast converging Federated Learning with Non-IID Data'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä