Joint Optimization for Social Content Dissemination in Wireless Networks
Over the last decade, success of social networks has significantly reshaped how information is disseminated among users in terms of scale, intensity and speed. Much effort, both academic and industrial, has been dedicated to learning the patterns of content dissemination to further facilitate it. However, as users become dominantly mobile in this process, little is done to consider the impact of the wireless environment, in particular, how to optimize the system in the presence of capacity shortage to better disseminate the contents. In this paper, we investigate how the wireless transmission delays degrade the performance of the content dissemination and propose a novel method to mitigate it. Results indicate that predictions of dissemination at social layer (even coarse ones) benefit the social dissemination, by improving scheduling performance at wireless layer. This in turn improves the accuracy of the predictions with user feedback. We also demonstrate that the system performance is greatly improved by introducing bias towards active user requests.