No abstract

Mobile edge computing is a new paradigm which provides cloud computing capabilities at the edge of pervasive radio access networks in close proximity to users. The problem of edge server selection in mobile edge environment in terms of user's overhead is investigated in this paper. Due to the limited resources of edge server, we firstly study the task completion probability of edge servers. Secondly, we formally model the problem of edge server selection in terms of time latency and energy consumption. More especially, the computation overhead method for completing the task in cases of both service migration and non-migration is investigated. Then, a new optimized edge server selection algorithm, called combined Genetic algorithm and simulated Annealing algorithm for edge Server Selection (GASS) is designed. Finally, a series of experiments on a real-word data-trace are conducted to evaluate the performance of GASS. The results show that GASS can effectively minimize the overhead of the user and outperform traditional heuristic algorithms.

Graph-based recommender system has attracted widespread attention and produced a series of research results. Because of the powerful high-order connection modeling capabilities of the Graph Neural Network (GNN), the performance of these graph-based recommender systems are far superior to those of traditional neural network-based collaborative filtering models. However, from both analytical and empirical perspectives, the apparent performance improvement is accompanied with a significant time overhead, which is noticeable in large-scale graph topologies. More importantly, the intrinsic data-sparsity problem substantially limits the performance of graph-based recommender systems, which compelled us to revisit graph-based recommendation from a novel perspective. In this paper, we focus on analyzing the time complexity of graph-based recommender systems to make it more suitable for real large-scale application scenarios. We propose a novel end-to-end graph recommendation model called the Collaborative Variational Graph Auto-Encoder (CVGA), which uses the information propagation and aggregation paradigms to encode user–item collaborative relationships on the user–item interaction bipartite graph. These relationships are utilized to infer the probability distribution of user behavior for parameter estimation rather than learning user or item embeddings. By doing so, we reconstruct the whole user–item interaction graph according to the known probability distribution in a feasible and elegant manner. From the perspective of the graph auto-encoder, we convert the graph recommendation task into a graph generation problem and are able to do it with approximately linear time complexity. Extensive experiments on four real-world benchmark datasets demonstrate that CVGA can be trained at a faster speed while maintaining comparable performance over state-of-the-art baselines for graph-based recommendation tasks. Further analysis shows that CVGA can effectively mitigate the data sparsity problem and performs equally well on large-scale datasets.

No abstract

No abstract