Filter pruning is an important technique to compress convolutional neural networks (CNNs) to acquire light-weight high-performance model for practical deployment. However, the existing filter pruning methods suffer from sharp performance drops when the pruning ratio is large, probably due to the unrecoverable information loss caused by aggressive pruning. In this paper, we propose a dual attention based pruning approach called DualPrune to push the limit of network pruning at an ultra-high compression ratio. Firstly, it adopts a graph attention network (GAT) to automatically extract filter-level and layer-level features from CNNs based on the roles of their filters in the whole computation graph. Then the extracted comprehensive features are fed to a side-attention network, which generates sparse attention weights for individual filters to guide model pruning. To avoid layer collapse, the side-attention network adopts a side-path design to preserve the information flow going through the CNN model properly, which allows the CNN model to be pruned at a high compression ratio at initialization and trained from scratch afterward. Extensive experiments based on several well-known CNN models and real-world datasets show that the proposed DualPrune method outperforms the state-of-the-art methods with significant performance improvement, particularly for model compression at a high pruning ratio.

In the current landscape of online data services, data transmission and cloud computing are often controlled separately by Internet Service Providers (ISPs) and cloud providers, resulting in significant cooperation challenges and suboptimal global data service optimization. In this study, we propose an end-to-end scheduling method aimed at supporting low-latency and computation-intensive medical services within local wireless networks and healthcare clouds. This approach serves as a practical paradigm for achieving low-latency data services in local private cloud environments. To meet the low-latency requirement while minimizing communication and computation resource usage, we leverage Deep Reinforcement Learning (DRL) algorithms to learn a policy for automatically regulating the transmission rate of medical services and the computation speed of cloud servers. Additionally, we utilize a two-stage tandem queue to address this problem effectively. Extensive experiments are conducted to validate the effectiveness for our proposed method under various arrival rates of medical services.

In mobile social networks, next point-of-interest (POI) recommendation is a very important function that can provide personalized location-based services for mobile users. In this paper, we propose a recurrent neural network (RNN)-based next POI recommendation approach that considers both the location interests of similar users and contextual information (such as time, current location, and friends’ preferences). We develop a spatial-temporal topic model to describe users’ location interest, based on which we form comprehensive feature representations of user interests and contextual information. We propose a supervised RNN learning prediction model for next POI recommendation. Experiments based on real-world dataset verify the accuracy and efficiency of the proposed approach, and achieve best F1-score of 0.196 754 on the Gowalla dataset and 0.354 592 on the Brightkite dataset.