Qimeng Yang

Multimodal intent detection leverages complementary information from diverse sensors to achieve precise semantic understanding; however, existing methodologies predominantly operate under the ideal assumption of modality completeness. In practical deployments, missing modalities, stemming from sensor failure, background noise, or privacy constraints, are inevitable and uncertain, leading to severe performance degradation. To address this challenge, we propose SADF, a Structure Aware Distillation Framework designed to facilitate robust cross-level knowledge transfer from a full-modality teacher to a partial-modality student. At the semantic level, semantic topology distillation aligns prototype similarity distributions between the teacher and the student, capturing class topology and hierarchical relations. At the discriminative level, boundary aware distillation decouples predictions into target and nontarget classes, enforcing alignment with the teacher to enhance discriminability and suppress noise. By integrating these strategies, SADF enables the student to learn robust representations and decisions when uncertain modalities are missing. The results of experiments based on two benchmarks demonstrate that SADF consistently outperforms strong baselines.

Circular RNA (circRNA) is a widely distributed class of non-coding RNA molecules that have been shown to play a significant role in cancer development and drug resistance, significantly influencing cellular sensitivity to therapeutic drugs and treatment outcomes. However, traditional biomedical experimental methods are limited by low efficiency and high costs when verifying the association between circular RNA and drug sensitivity. Therefore, developing an efficient and accurate computational method to predict new associations between circRNA and drug sensitivity has become an urgent need in current research. To address this, this study proposes HECLCDA, a novel method based on heterogeneous cross-scale contrastive learning. To construct a comprehensive initial information base for drugs and circRNAs, circRNA gene sequence similarity, drug structural inclusion similarity (SIS), and Gaussian kernel similarity were integrated. Based on the integrated and complete known information of circRNAs and drugs, a heterogeneous graph was built. The model used the Heterogeneous Graph Transformer to extract heterogeneous network topological information, effectively distinguishing the heterogeneity of nodes and edges. The model broke through the information relationship between node attributes and network topology at two scales, and innovatively introduced a cross-scale contrastive learning mechanism in a sparse labeling scenario. Using self-supervised signals, we aimed to enhance the discriminative power of node embeddings and maximize the mutual information between paired nodes at different scales. Cross-validation experiments demonstrated that HECLCDA performs excellently on real data and can efficiently predict drug sensitivity. Additionally, case studies further validate the model's effectiveness in predicting potential circRNA-drug sensitivity associations.

The proliferation of smart devices in recent years has fostered unprecedented levels of connectivity, giving rise to a novel paradigm known as Compute First Networking (CFN). This paradigm is designed to optimize and efficiently utilize both network and computing resources. However, the proliferation of network intrusions poses security challenges. Deep learning (DL)-based Network Intrusion Detection Systems (NIDS) can be hardly supported by edge smart gateways. Edge computing enables near-real-time analysis of network intrusions by offloading AI-intensive tasks from edge gateways to cloud servers. Coordinating computing task offloading among multiple edges is challenging due to varying channel conditions and stringent latency requirements of NIDS. To address this challenge, we propose a multi-edge collaborative framework for NIDS. Given the complexity of AI-enabled NIDS, we introduce a delay-aware computational offloading strategy to minimize latency. In addition, inspired by the non-Euclidean nature of network data and its abundant chronological and temporal relations, we design a Node-Level Attention-Based Auto-Encoder Graph Convolutional Network (NAAE-GCN) to capture latent behavioral patterns of evolving network attacks. Experimental results show that the proposed NAAE-GCN achieves new state-of-the-art results in the detection performance with significant improvements over existing approaches.