This research suggests a multi-level federated edge learning algorithm by leveraging the advantages of Edge Computing Paradigm. Model aggregation is partially moved from a cloud center server to edge servers in this framework, and edge servers are connected hierarchically depending on where they are located and how much computational power they have. At the same time, we considered an important issue: the heterogeneity of different client computing resources (such as device processor computing power) and server communication channels (which may be limited by geography or device). For this situation, a client and edge server selection algorithm ($CESA$) based on a greedy algorithm is proposed in this paper. Given resource constraints, $CESA$ aims to select as many clients and edge servers as possible to participate in the model computation in order to improve the accuracy of the model. The simulation results show that, when the number of clients is high, the multi-level federated edge learning algorithm can shorten the model training time and improve efficiency compared to the traditional federated learning algorithm. Meanwhile, the $CESA$ is able to aggregate more clients for training in the same amount of time compared to the baseline algorithm, improving model training accuracy.

Users who initiate continuous location queries are prone to trajectory information leakage, and the obtained query information is not effectively utilized. To address these problems, we propose a continuous location query protection scheme based on caching and an adaptive variable-order Markov model. When a user initiates a query request, we first query the cache information to obtain the required data. When the local cache cannot satisfy the user’s demand, we use a variable-order Markov model to predict the user’s future query location and generate a k-anonymous set based on the predicted location and cache contribution. We perturb the location set using differential privacy, then send the perturbed location set to the location service provider to obtain the service. We cache the query results returned by the service provider to the local device and update the local cache results according to time. By comparing the experiment with other schemes, the proposed scheme in this paper reduces the number of interactions with location providers, improves the local cache hit rate, and effectively ensures the security of the users’ location privacy.

Most Heterogeneous Information Network (HIN) embedding methods use meta-paths to guide random walks to sample from HIN and perform representation learning in order to overcome the bias of traditional random walks that are more biased towards high-order nodes. Their performance depends on the suitability of the generated meta-paths for the current HIN. The definition of meta-paths requires domain expertise, which makes the results overly dependent on the meta-paths. Moreover, it is difficult to represent the structure of complex HIN with a single meta-path. In a meta-path guided random walk, some of the heterogeneous structures (e.g., node type(s)) are not among the node types specified by the meta-path, making this heterogeneous information ignored. In this paper, HeteEdgeWalk, a solution method that does not involve meta-paths, is proposed. We design a dynamically adjusted bidirectional edge-sampling walk strategy. Specifically, edge sampling and the storage of recently selected edge types are used to better sample the network structure in a more balanced and comprehensive way. Finally, node classification and clustering experiments are performed on four real HINs with in-depth analysis. The results show a maximum performance improvement of 2% in node classification and at least 0.6% in clustering compared to baselines. This demonstrates the superiority of the method to effectively capture semantic information from HINs.