Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. However, directly averaging model parameters is only possible if all models have the same structure and size, which could be a restrictive constraint in many scenarios. In this work we investigate more powerful and more flexible aggregation schemes for FL. Specifically, we propose ensemble distillation for model fusion, i.e. training the central classifier through unlabeled data on the outputs of the models from the clients. This knowledge distillation technique mitigates privacy risk and cost to the same extent as the baseline FL algorithms, but allows flexible aggregation over heterogeneous client models that can differ e.g. in size, numerical precision or structure. We show in extensive empirical experiments on various CV/NLP datasets (CIFAR-10/100, ImageNet, AG News, SST2) and settings (heterogeneous models/data) that the server model can be trained much faster, requiring fewer communication rounds than any existing FL technique so far.

Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. However, directly averaging model parameters is only possible if all models have the same structure and size, which could be a restrictive constraint in many scenarios. In this work we investigate more powerful and more flexible aggregation schemes for FL. Specifically, we propose ensemble distillation for model fusion, i.e. training the central classifier through unlabeled data on the outputs of the models from the clients. This knowledge distillation technique mitigates privacy risk and cost to the same extent as the baseline FL algorithms, but allows flexible aggregation over heterogeneous client models that can differ e.g. in size, numerical precision or structure.

Strengths: This work manifests solid understanding of key requirements and challenges of federated learning, and thus presents a practical solution with significant improvements. The contribution of this paper is formulating a robust, efficient training scheme in FL with extensive results and analysis, which is relevant to the NeurIPS community. They provide sufficient justifications about why the additional computations are negligible in practice and why the reduced number of communication rounds and the ability to handle architecture heterogeneity of FedDF matter more. The authors analyzed its contribution from various angles including efficiency, utilizing heterogeneous computation resources of clients, robustness on the choice of distillation dataset, and handling heterogeneous client data by mitigating quality loss of batch normalization with different data distributions. The results are sensible and believable.

I recommend this paper for acceptance. The paper is on an important and a timely topic and is above the quality bar necessary for acceptance. Although the reviewers had some concerns, the rebuttal clarified their most burning questions. I also thought that the more critical reviews were the less informed ones. Having said that, I strongly suggest to take all comments of the reviewers into account to improve the quality of the camera-ready version, mostly with respect to the organization, the clarity of the paper (including the description of the related work) and including the results provided in the rebuttal.

Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. However, directly averaging model parameters is only possible if all models have the same structure and size, which could be a restrictive constraint in many scenarios. In this work we investigate more powerful and more flexible aggregation schemes for FL. Specifically, we propose ensemble distillation for model fusion, i.e. training the central classifier through unlabeled data on the outputs of the models from the clients. This knowledge distillation technique mitigates privacy risk and cost to the same extent as the baseline FL algorithms, but allows flexible aggregation over heterogeneous client models that can differ e.g. in size, numerical precision or structure.