Few-shot classification is increasingly relevant in emerging applications, such as university course classification in intelligent education systems. University course classification helps students acquire specific skills, comprehend course purposes, and assists departments in defining training goals. However, classifying frontier courses presents challenges due to the absence of labels and descriptions. Few-shot learning addresses this by acquiring meta-knowledge. Heterogeneous graphs (HGs), rich in semantic information, introduce complexities that make few-shot particularly challenging. Addressing this problem, we propose a subgraph-aware convolutional few-shot classification method on HGs (HG-SCC). We first formalize the subgraph sampling strategy for HGs and different views under meta-paths. Then, the layer number adaptive spectral-based graph convolution is designed for personalized node embedding. Furthermore, a high-order convolution operation with classes as nodes is designed to increase the class representation coverage. Modeling subgraph centrality, combined with node features, captures structural information, improving awareness of each sampled subgraph, thus alleviating sparsity in new class labels and enhancing classification accuracy. Euclidean distance-based and task-affected cosine similarity-based classifiers under different meta-paths are proposed, with stacking introduced to blend multiple classifiers based on subgraph features. Experimental results show that our method has high performance in course classification and also outperforms state-of-the-art methods on benchmark datasets.

The Internet of Vehicles (IoV) faces critical challenges in balancing real-time data processing, privacy preservation, and secure data sharing amid growing intelligent transportation demands. While mobile edge computing (MEC) reduces latency by offloading tasks to MEC servers, efficient encrypted search and dynamic access control remain unresolved. Attribute-based keyword search (ABKS) enables privacy-preserving queries on encrypted data but exhibits critical limitations such as lack of revocable access for dynamic user privileges, exposed access policy that risk sensitive attribute leakage, and data integrity verification. Moreover, existing ABKS schemes further suffer from centralized key management in attribute-based encryption (ABE), introducing single points of failure and key escrow issues. To address these issues, we propose BC-RMABSE, a blockchain-enabled ABKS scheme. Our scheme leverages the vector space model to enable ranked multi-keyword searches, returning top-k relevant results for improved efficiency. Policy-hiding mechanisms and attribute revocation ensure flexible fine-grained access control while safeguarding sensitive attributes. A decentralized key distribution strategy using Pedersen’s (k, n) secret sharing protocol eliminates reliance on central authority, mitigating security risks. Blockchain technology enforces data integrity through tamper-proof consensus and resolves the "service-payment" imbalance via smart contracts, ensuring transactional fairness between users and untrusted service providers. Experimental analysis indicates that our scheme performs well in terms of both security and search efficiency.