In recent years, methods based on heterogeneous graph neural networks (HGNNs) have been widely used for embedding heterogeneous graphs (HGs) due to their ability to effectively encode the rich information from HGs into low-dimensional node embeddings. Existing HGNNs focus on neighbor aggregation and semantic fusion while neglecting the HG structure and learning paradigms. However, the original HG data might lack node features, which existing models may not effectively account for. Additionally, exclusively relying on a single supervised learning approach may only partially leverage the invariant information in graph data. To address these challenges, we introduce the Contrastive Auxiliary Learning Model for Heterogeneous Graphs (CALHG). This model combines edge perturbation and graph diffusion to enhance graph data, allowing it to capture the inherent structural information within heterogeneous graphs fully. Additionally, we employ a category-guided multi-view contrastive learning approach, which does not rely on positive and negative samples for model training, enabling us to capture the intrinsic invariances in heterogeneous graph data. Extensive experiments and analyses on five benchmark datasets without node features and three benchmark datasets with node features demonstrate the effectiveness and efficiency of our novel method compared with several state-of-the-art methods.

In order to solve the problem that high-priority tasks can not be processed timely and reliably due to the disorder of multi-task and dynamicity in Power Internet of Things(PIoTs), a high-reliability small-area task offloading mechanism with trust evaluation and fuzzy logic(HRSATF) is proposed. First, considering task priority, preemptive priority queue is introduced to ensure high-priority tasks processed preferentially, and minimum resource allocation coefficients(MRACs) of tasks are solved to ensure the effectiveness of offloading. Second, the trust model between smart device(SD) and edge server(ES) is established, and ESs are divided into three priorities based on trust value and computing power by fast non-dominated sorting. Thirdly, fuzzy logic is applied to select target ES when the priorities of task and ES do not match or the ES is offline, and MRAC is used to schedule tasks between SD and ES. Finally, NSGA2 is modified (MNSGA2) to verify the effectiveness of HRSATF in terms of success rate, time, power consumption and load balancing, where success rate is increased by$102.3\%$, and time and power consumption are decreased by$90.7\%$,$89.3\%$at most, respectively.

Abstract With more and more interconnected smart devices (ISDs) accessing the Internet of Things (IoT), massive and diverse tasks need to be transformed and computed. Mobile edge computing enables the offloading of tasks to nearby servers to enhance processing efficiency, which makes ISDs idle, causing resource waste and failing to satisfy the high real‐time requirements of tasks. Besides, when tasks with different priorities are processed in the order they are generated, it will be difficult for IoT to guarantee a timely response to high‐priority tasks. To address the aforementioned issues, we establish an edge‐terminal‐local architecture by software‐defined networking to centrally manage idle ISD resource (2ISDR). Then the proposed two‐step scheduling mechanism with preemptive priority queue ensures the real‐time responses to high‐priority tasks, and the minimum resource allocation coefficients make offloading effective. Finally, we also propose a modified NSGA‐III algorithm named MNSGA‐III, which is designed to make decisions about offloading and solve resource allocation for tasks, and we correct infeasible solutions by a two‐step correction function to ensure the feasibility of MNSGA‐III. Experimental results show that the method can ensure a timely response to high‐priority tasks and optimize processing time, energy consumption, and economic cost through the utilization of 2ISDR.