Federated learning (FL) is a novel machine learning setting that enables on-device intelligence via decentralized training and federated optimization. Deep neural networks' rapid development facilitates the learning techniques for modeling complex problems and emerges into federated deep learning under the federated setting. However, the tremendous amount of model parameters burdens the communication network with a high load of transportation. This paper introduces two approaches for improving communication efficiency by dynamic sampling and top-k selective masking. The former controls the fraction of selected client models dynamically, while the latter selects parameters with top-k largest values of difference for federated updating. Experiments on convolutional image classification and recurrent language modeling are conducted on three public datasets to show our proposed methods' effectiveness.

No abstract

Learning embedding spaces of suitable geometry is critical for representation learning. In order for learned representations to be effective and efficient, it is ideal that the geometric inductive bias aligns well with the underlying structure of the data. In this paper, we propose Switch Spaces, a data-driven approach for learning representations in product space. Specifically, product spaces (or manifolds) are spaces of mixed curvature, i.e., a combination of multiple euclidean and noneuclidean (hyperbolic, spherical) manifolds. To this end, we introduce sparse gating mechanisms that learn to choose, combine and switch spaces, allowing them to be switchable depending on the input data with specialization. Additionally, the proposed method is also efficient and has a constant computational complexity regardless of the model size. Experiments on knowledge graph completion and item recommendations show that the proposed switch space achieves new state-ofthe-art performances, outperforming pure product spaces and recently proposed task-specific models.

Alongside with the convergence of In-vehicle network (IVN) and wireless communication technology, In-vehicle CAN communication with external networks reinforces the connectivity among systems of a vehicle. Vehicle communication is facing severe challenges. Intrusion detection technology is one of the most widely used technologies to ensure the safety of In-vehicle CAN communication, so an adaptive intrusion detection method for In-vehicle CAN bus based on message periodicity is proposed. Communication load of CAN bus in the vehicle, the unique priority mechanism and transmission waiting mechanism of CAN message cause a certain fluctuation in the message cycle. The influence of this fluctuation on the detection accuracy of intrusion detection algorithm is analysed while rules are determined by establishing and optimizing the detection threshold in order to further improve the accuracy. Experimental results show that the adaptive intrusion detection based on message periodicity can effectively detect injection and interruption attacks.