TY - JOUR A1 - Song, Rui A1 - Zhou, Liguo A1 - Lyu, Lingjuan A1 - Festag, Andreas A1 - Knoll, Alois T1 - ResFed: Communication-Efficient Federated Learning With Deep Compressed Residuals JF - IEEE Internet of Things Journal N2 - Federated learning allows for cooperative training among distributed clients by sharing their locally learned model parameters, such as weights or gradients. However, as model size increases, the communication bandwidth required for deployment in wireless networks becomes a bottleneck. To address this, we propose a residual-based federated learning framework (ResFed) that transmits residuals instead of gradients or weights in networks. By predicting model updates at both clients and the server, residuals are calculated as the difference between updated and predicted models and contain more dense information than weights or gradients. We find that the residuals are less sensitive to an increasing compression ratio than other parameters, and hence use lossy compression techniques on residuals to improve communication efficiency for training in federated settings. With the same compression ratio, ResFed outperforms current methods (weight- or gradient-based federated learning) by over 1.4× on federated data sets, including MNIST, FashionMNIST, SVHN, CIFAR-10, CIFAR-100, and FEMNIST, in client-to-server communication, and can also be applied to reduce communication costs for server-to-client communication. UR - https://doi.org/10.1109/JIOT.2023.3324079 Y1 - 2023 UR - https://doi.org/10.1109/JIOT.2023.3324079 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-46371 SN - 2327-4662 VL - 11 IS - 6 SP - 9458 EP - 9472 PB - IEEE CY - New York ER - TY - INPR A1 - Song, Rui A1 - Zhou, Liguo A1 - Lyu, Lingjuan A1 - Festag, Andreas A1 - Knoll, Alois T1 - ResFed: Communication Efficient Federated Learning by Transmitting Deep Compressed Residuals UR - https://doi.org/10.48550/arXiv.2212.05602 Y1 - 2022 UR - https://doi.org/10.48550/arXiv.2212.05602 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Song, Rui A1 - Lyu, Lingjuan A1 - Jiang, Wei A1 - Festag, Andreas A1 - Knoll, Alois T1 - V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection T2 - CoPerception: Collaborative Perception and Learning, ICRA 2023 workshop Y1 - 2023 UR - https://drive.google.com/file/d/1-OQAeNryd7-lksCTuWnhhyydpFSnw5On/view?usp=share_link ER - TY - INPR A1 - Song, Rui A1 - Lyu, Lingjuan A1 - Jiang, Wei A1 - Festag, Andreas A1 - Knoll, Alois T1 - V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection N2 - Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services. Federated learning (FL) overcomes privacy constraints by training ML models in distributed systems, exchanging model parameters instead of raw data. However, the dynamic states of connected vehicles affect the network connection quality and influence the FL performance. To tackle this challenge, we propose a contextual client selection pipeline that uses Vehicle-to-Everything (V2X) messages to select clients based on the predicted communication latency. The pipeline includes: (i) fusing V2X messages, (ii) predicting future traffic topology, (iii) pre-clustering clients based on local data distribution similarity, and (iv) selecting clients with minimal latency for future model aggregation. Experiments show that our pipeline outperforms baselines on various datasets, particularly in non-iid settings. UR - https://doi.org/10.48550/arXiv.2305.11654 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2305.11654 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41441 PB - arXiv CY - Ithaca ER -