Human motion prediction is a key task in computer vision and human-robot interaction, which has received much attention in recent years. However, existing approaches suffer from two issues: 1) They typically rely only on complete data and overlook real-world challenges such as missing observations. 2) Recent works fail to capture the diverse relations among body parts in different action categories, which limits their prediction performance. To address the above problems, we propose a novel Incomplete human Motion Prediction method through motion Re covery and Structure-Semantic fusion (IMPRESS). Specifically, for motion recovery, we introduce a wavelet-based self-attention module. It captures motion details from high-frequency features and extracts global trends from low-frequency components. To enhance the relations among different body parts, we design a structure-semantic fusion graph convolutional network. Moreover, we employ a dual-channel sliding window attention mechanism to capture motion periodicity, enabling smoother predictions. Extensive experiments on two benchmark datasets (Human3.6M, CMU-MoCap) demonstrate that IMPRESS achieves state-of-the-art average prediction performance under both complete and incomplete observations.

Fault diagnosis for high-dimensional industrial process data with strong nonlinear coupling remains challenging. Most existing graph convolutional network–based methods rely on static or single graph structures, which limits their ability to jointly capture physical consistency and time-varying data characteristics. In addition, fixed feature fusion strategies lack adaptability to diverse fault patterns. To overcome these limitations, this paper proposes a Dual-Stream Fusion Graph Convolution Network (DSFGCN) that integrates knowledge-driven and data-driven information in a complementary manner. Specifically, a dual-graph construction mechanism is developed, where a knowledge graph incorporates expert prior information to preserve physical interpretability, while a supervised manifold graph based on Discriminative Locality Preserving Projections captures intrinsic nonlinear data structures. Furthermore, an adaptive gated fusion unit is designed to dynamically adjust the contributions of the two graph streams according to operating conditions. Experiments on the Tennessee Eastman Process and Multiphase Flow Facility datasets demonstrate that DSFGCN achieves superior diagnostic accuracy and robustness, particularly for complex nonlinear fault scenarios.

Graph convolutional networks (GCNs) can effectively learn graph data features and are widely used to predict the bearing remaining useful life (RUL). However, most existing GCN-based methods are based on single-node relationships to construct the graph structure while ignoring potential complex relationships between nodes. To enrich graph feature information and improve bearing RUL prediction accuracy, a novel bearing RUL prediction method is proposed in this article, which use spatial–temporal information fusion graph convolution network. The proposed method mines implicit temporal dependence and spatial correlation in graph samples by constructing PathGraph and RadiusGraph, which effectively improves the feature diversity of graph samples. In addition, to efficiently extract the spatial–temporal features of graph samples and alleviate the over-smoothing problem in GCNs, a feature extraction module combining graph attention network (GAT) and graph convolution network–temporal convolution network (GCN-TCN) is designed, where GAT dynamically assigns edge weights to capture spatial dependencies, while GCN-TCN enhances global temporal dependency capture. The experimental validation results show that the proposed method effectively improves bearing RUL prediction accuracy.

Hierarchical Attentional Fusion Graph Attention Network for Marine Diesel Engines Based on Imbalanced Datasets

Decoupled multi-spatio-temporal fusion graph convolutional recurrent network for traffic prediction

Code search has received significant attention in the field of computer science research. Its core objective is to retrieve the most semantically relevant code snippets by aligning the semantics of natural language queries with those of programming languages, thereby contributing to improvements in software development quality and efficiency. As the scale of public code repositories continues to expand rapidly, the ability to accurately understand and efficiently match relevant code has become a critical challenge. Furthermore, while numerous studies have demonstrated the efficacy of deep learning in code-related tasks, the mapping and semantic correlations are often inadequately addressed, leading to the disruption of structural integrity and insufficient representational capacity during semantic matching. To overcome these limitations, we propose the Functional Program Graph for Code Search (called FPGraphCS), a novel code search method that leverages the construction of functional program graphs and an early fusion strategy. By incorporating abstract syntax tree (AST), data dependency graph (DDG), and control flow graph (CFG), the method constructs a comprehensive multigraph representation, enriched with contextual information. Additionally, we propose an improved metapath aggregation graph neural network (IMAGNN) model for the extraction of code features with complex semantic correlations from heterogeneous graphs. Through the use of metapath-associated subgraphs and dynamic metapath selection via a graph attention mechanism, FPGraphCS significantly enhances its search capability. The experimental results demonstrate that FPGraphCS outperforms existing baseline methods, achieving an MRR of 0.65 and ACC@10 of 0.842, showing a significant improvement over previous approaches.

Accurate prediction of microbe-drug associations (MDAs) is vital for guiding antimicrobial therapy and accelerating drug repositioning. Although experimental validation remains the gold standard, it is costly and time-consuming. Existing models, often based on similarity fusion or conventional graph neural networks (GNNs), struggle to capture the heterogeneous and multiscale interaction patterns of biomedical networks. We present HGANMDA, a heterogeneous graph adversarial network for MDA prediction. The framework integrates multimodal biological information into a unified heterogeneous graph, employs a multichannel structural encoder with attention-based aggregation to capture local and global patterns, and introduces adversarial embedding regularization to enhance robustness and feature separability. Experiments on three benchmark data sets show that HGANMDA consistently outperforms state-of-the-art baselines across multiple metrics. These results highlight the potential of adversarially regularized heterogeneous graph learning in supporting antimicrobial research.

Traffic flow prediction presents significant challenges in modeling complex spatiotemporal dependencies and quantifying uncertainties. We propose MSDA-DiffNet, a novel framework that integrates three key components: a Multi-Scale Feature Fusion Module that captures temporal dependencies across various scales; a Dual Adaptive Graph Convolution Network that dynamically models spatial correlations; and a Conditional Diffusion Module that generates probabilistic predictions with comprehensive uncertainty quantification. Our approach addresses the limitations of existing methods that rely on static graph structures and single-scale features. Extensive experiments conducted on four public datasets demonstrate that MSDA-DiffNet significantly outperforms state-of-the-art models, reducing Mean Absolute Error, Mean Absolute Percentage Error, and Root Mean Square Error by 8.9%, 7.5%, and 9.3% respectively, while providing robust uncertainty estimation.

Urban scene segmentation is essential for 3D city modeling and plays a crucial role in various remote sensing applications, including urban planning and environmental monitoring. While integrating knowledge graphs with scene segmentation has improved accuracy, existing methods often depend on dataset-specific knowledge graphs, limiting their generalizability across diverse remote sensing data. To address this, we propose a novel framework that leverages large language models (LLMs) to construct a universal knowledge graph from multi-source geospatial data and incorporate it into remote sensing semantic segmentation tasks, enhancing adaptability and robustness in urban scene understanding. Specifically, the framework comprises two key components: (1) a Graph Construction module that employs LLMs to extract cross-domain semantic relationships and build a universal knowledge graph, and (2) a Knowledge Graph Fusion module (KGFusion) that incorporates the graph into a semantic segmentation network to enhance semantic understanding. To evaluate the adaptability of our method across diverse domains, we curated a mixed dataset encompassing urban, rural, and port scenes. Experimental findings validate the efficiency and adaptability of our method, achieving 70.94% mIoU on the UAVid dataset and 63.23% on the Mixed dataset, outperforming the baseline by 0.43% and 1.04%, respectively. These results validate the robustness of our method in cross-domain scenarios and highlight its potential for broader applications in complex urban environments.

MiRNA serves as a key noncoding RNA regulating gene expression and is frequently targeted as a therapeutic small molecule (SM). However, relying solely on the experimental identification of SM-miRNA interactions proves costly and inefficient. To address this, this paper proposes an SM-miRNA association prediction method according to attention-based multimodal fusion and variational graph learning (AttMVGraph). The method utilizes Random Walk with Restarts (RWR) topological features and SM/miRNA similarity as multimodal inputs. Adaptive weighted fusion is achieved through feature-enhanced channel attention (FECA), yielding discriminative graph embeddings. Subsequently, a Variational Graph Autoencoder (VGAE) is employed for uncertainty modeling and representation learning. During prediction, a dynamic hard negative mining (DHNM) mechanism is introduced to iteratively select hard negative samples, mitigating extreme positive-negative sample imbalance and strengthening decision boundaries. 5-CV showed that the model produced excellent results, with an AUC = 0.9937 ± 0.0061 (AUC = 0.9727 ± 0.0001) and AUPR = 0.9397 ± 0.0753 (0.8807 ± 0.0589) in Dataset 1 (Dataset 2), verifying the effectiveness and superiority of AttMVGraph. All our data and codes have been uploaded to https://github.com/tr612-maker/AttMVGraph-master.

MGFN-WR: multi-modal knowledge graph completion with multi-layer graph fusion network based on weight regulation

In real-world conditions, data typically contain multiple modalities and may have non-exclusive labels. A key stage of multimodal learning is the process of multimodal fusion, as it enables the integration of features from different sources into a unified vector space. This allows the classifier to utilize the constructed integrated vector to produce the final prediction. At the same time, traditional multimodal fusion methods rarely take into account cross-modal interactions, which play an essential role in uncovering dependencies between modalities and in constructing a shared space of their integrated representation. In this paper, we propose a conceptual framework for multimodal fusion with the use of multi-task learning. It is aimed at modeling a joint integrated representation space for all cross-modal interactions and adaptively tuning the loss functions of individual tasks in order to achieve optimal performance. The developed model employs a novel hierarchical multimodal fusion network that captures cross-modal interactions across all modality combinations and dynamically allocates weight coefficients for each pair depending on the specific data sample. In addition, a new multi-task learning approach is introduced to address multi-label classification challenges by automatically adjusting the training process both at the task level and at the sample level. Experimental results demonstrate that the proposed conceptual framework outperforms baseline models as well as several state-of-the-art methods. Furthermore, the flexibility and modularity of the proposed components of multimodal fusion and dynamic multi-task learning are showcased, making them applicable to various types of neural network architectures.

Load probabilistic forecasting for electric vehicle charging station cluster: Adaptive multivariate spatiotemporal graph fusion technology

Spleen-Stomach disorders are prevalent clinical conditions in Traditional Chinese Medicine (TCM). The complex diagnostic and treatment model used in TCM is based on a "symptom-pattern-disease-formula" framework that heavily relies on practitioners' experience. However, this model faces several challenges, including ambiguous knowledge representation, unstructured data, and difficulties with knowledge sharing. Recent advancements in artificial intelligence, natural language processing, and medical knowledge engineering have significantly improved research on knowledge graphs (KGs) and intelligent diagnosis and treatment systems for these disorders, making these technologies crucial for modernizing TCM. This article systematically reviews two core research pathways related to Spleen-Stomach disorders. The first pathway focuses on constructing knowledge graphs for "structured knowledge representation". This includes ontology modeling, entity recognition, relation extraction, graph fusion, semantic reasoning, visualization services, and an ensemble model to predict treatment efficacy. The second pathway involves the development of intelligent diagnosis and treatment systems, with a focus on "clinical applications". This pathway includes key technologies such as quantitative modeling of TCM, the four diagnostic methods (inspection, auscultation-olfaction, interrogation, and palpation), semantic analysis of classical texts, pattern differentiation algorithms, and multimodal consultation recommenders. Through the synthesis and analysis of current research, several ongoing challenges have been identified. These include inconsistent models and annotation of TCM clinical knowledge, limited semantic reasoning capabilities, insufficient integration between KGs and intelligent diagnostic models, and limited clinical adaptability of existing intelligent diagnostic systems. To address these challenges, this review suggests future research directions that include enhancing heterogeneous multisource knowledge integration techniques, deepening semantic reasoning through collaborative reasoning frameworks that incorporate large language models, and developing effective cross-disease transfer learning strategies. These directions aim to improve interpretability, reasoning accuracy, and clinical applicability of intelligent diagnosis and treatment systems for Spleen-Stomach disorders in TCM.

Intelligence on the Graph: Graph Neural Networks for Mechanistic Drug Target Discovery

WITHDRAWN: Incomplete multi-view clustering based on kernel graph fusion tensor under self-expression framework

Auto-weighted graph tensor and rank-constrained bipartite graph fusion for multi-view clustering

CBH-YOLO: A steel surface defect detection algorithm based on cross-stage Mamba enhancement and hierarchical semantic graph fusion

Radio map estimation (RME) is a crucial method for analyzing spectrum space utilization and network coverage, serving as an essential tool for the mobile communication. However, physical constraints, security, privacy, and other issues often render some areas inaccessible, resulting in extremely sparse and unevenly distributed measurement data. To address these challenges, we propose a multimodal feature fusion graph convolution network (MFFGCN). The model incorporates a dual-encoder architecture with an adaptive multi-feature fusion module to exploit environmental information and learn the shadowing effects of radio-signal propagation. We then convert the coarse estimation into regional feature patches and construct a graph over these patches. A graph neural network aggregates contextual information among them, thereby alleviating the impact of uneven spatial sampling. Extensive experiments on open datasets demonstrate that our method achieves state-of-the-art performance, effectively reducing the effects of uneven sampling.

Multi-intent prediction of scientific literature based on heterogeneous graph fusion network