Publications

@inproceedings{li2021fedbn,

title = {FedBN: Federated Learning on Non-IID Features via Local Batch Normalization},

author = {Xiaoxiao Li and Meirui Jiang and Xiaofei Zhang and Michael Kamp and Qi Dou},

url = {https://michaelkamp.org/wp-content/uploads/2021/05/fedbn_federated_learning_on_non_iid_features_via_local_batch_normalization.pdf

https://michaelkamp.org/wp-content/uploads/2021/05/FedBN_appendix.pdf},

year  = {2021},

date = {2021-05-03},

urldate = {2021-05-03},

booktitle = {Proceedings of the 9th International Conference on Learning Representations (ICLR)},

abstract = {The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data and hence improving data privacy. In most cases, the assumption of independent and identically distributed samples across local clients does not hold for federated learning setups. Under this setting, neural network training performance may vary significantly according to the data distribution and even hurt training convergence. Most of the previous work has focused on a difference in the distribution of labels or client shifts. Unlike those settings, we address an important problem of FL, e.g., different scanners/sensors in medical imaging, different scenery distribution in autonomous driving (highway vs. city), where local clients store examples with different distributions compared to other clients, which we denote as feature shift non-iid. In this work, we propose an effective method that uses local batch normalization to alleviate the feature shift before averaging models. The resulting scheme, called FedBN, outperforms both classical FedAvg, as well as the state-of-the-art for non-iid data (FedProx) on our extensive experiments. These empirical results are supported by a convergence analysis that shows in a simplified setting that FedBN has a faster convergence rate than FedAvg. Code is available at https://github.com/med-air/FedBN.},

keywords = {batch normalization, black-box parallelization, deep learning, federated learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kamp2018efficient,

title = {Efficient Decentralized Deep Learning by Dynamic Model Averaging},

author = {Michael Kamp and Linara Adilova and Joachim Sicking and Fabian Hüger and Peter Schlicht and Tim Wirtz and Stefan Wrobel},

url = {http://michaelkamp.org/wp-content/uploads/2018/07/commEffDeepLearning_extended.pdf},

year  = {2018},

date = {2018-09-14},

booktitle = {Machine Learning and Knowledge Discovery in Databases},

publisher = {Springer},

abstract = {We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model training equally well and to quickly adapt to concept drifts. This leads to a reduction of communication by an order of magnitude compared to periodically communicating state-of-the-art approaches. Moreover, we derive a communication bound that scales well with the hardness of the serialized learning problem. The reduction in communication comes at almost no cost, as the predictive performance remains virtually unchanged. Indeed, the proposed protocol retains loss bounds of periodically averaging schemes. An extensive empirical evaluation validates major improvement of the trade-off between model performance and communication which could be beneficial for numerous decentralized learning applications, such as autonomous driving, or voice recognition and image classification on mobile phones.},

keywords = {decentralized, deep learning, federated learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kamp2016communication,

title = {Communication-Efficient Distributed Online Learning with Kernels},

author = {Michael Kamp and Sebastian Bothe and Mario Boley and Michael Mock},

editor = {Paolo Frasconi and Niels Landwehr and Giuseppe Manco and Jilles Vreeken},

url = {http://michaelkamp.org/wp-content/uploads/2020/03/Paper467.pdf},

year  = {2016},

date = {2016-09-16},

urldate = {2016-09-16},

booktitle = {Machine Learning and Knowledge Discovery in Databases},

pages = {805--819},

publisher = {Springer International Publishing},

abstract = {We propose an efficient distributed online learning protocol for low-latency real-time services. It extends a previously presented protocol to kernelized online learners that represent their models by a support vector expansion. While such learners often achieve higher predictive performance than their linear counterparts, communicating the support vector expansions becomes inefficient for large numbers of support vectors. The proposed extension allows for a larger class of online learning algorithms—including those alleviating the problem above through model compression. In addition, we characterize the quality of the proposed protocol by introducing a novel criterion that requires the communication to be bounded by the loss suffered.},

keywords = {communication-efficient, distributed, dynamic averaging, federated learning, kernel methods, parallelization},

pubstate = {published},

tppubtype = {inproceedings}

}