Search Results (1,912)

Graph representation learning (GRL) has emerged as a unifying paradigm for modeling the relational and heterogeneous nature of battery energy storage systems (BESS), yet a systematic synthesis focused on data-scarce (few-shot) battery scenarios is still lacking. Graph representation learning offers a natural way to describe the structure and interaction of battery cells, modules and packs. At the same time, battery applications often suffer from very limited labeled data, especially for new chemistries, extreme operating conditions and second-life use. This review analyzes how graph representation learning can be combined with few-shot learning to support key battery management tasks under such data-scarce conditions. We first introduce the basic ideas of graph representation learning, including models based on neighborhood aggregation, contrastive learning, autoencoders and transfer learning, and discuss typical data, model and algorithm challenges in few-shot scenarios. We then connect these methods to battery state estimation problems, covering state of charge, state of health, remaining useful life and capacity. Particular attention is given to approaches that use graph neural models, meta-learning, semi-supervised and self-supervised learning, Bayesian deep networks, and federated learning to extract transferable features from early-cycle data, partial charge–discharge curves and large unlabeled field datasets. Reported studies show that, with only a small fraction of labeled samples or a few initial cycles, these methods can achieve state and life prediction errors that are comparable to or better than conventional models trained on full datasets, while also improving robustness and, in some cases, providing uncertainty estimates. Based on this evidence, we summarize the main technical routes for few-shot battery scenarios and identify open problems in data preparation, cross-domain generalization, uncertainty quantification and deployment on real battery management systems. The review concludes with a research outlook, highlighting the need for pack-level graph models, physics-guided and probabilistic learning, and unified benchmarks to advance reliable graph-based few-shot methods for next-generation intelligent battery management. Full article

With the proliferation of mobile devices, identifying previously unseen mobile applications has become a critical challenge in network security. Traditional application identification approaches rely heavily on fixed training categories and limited traffic features, making them ineffective in real-world environments. To address this problem, we propose KZGNN, a knowledge-enhanced zero-shot graph neural network for mobile application identification. KZGNN first constructs a unified mobile application knowledge graph that integrates high-level semantic metadata with fine-grained network behavior, enabling structured representation of application characteristics. Building on this, KZGNN introduces a relation-aware dual-channel propagation mechanism that separates semantic relations and behavioral interactions into dedicated GNN pathways and adaptively fuses them through attention. To support zero-shot recognition, KZGNN projects node embeddings and category semantics into a shared embedding space, where a structure-preserving constraint maintains global semantic geometry and improves generalization to unseen categories. Experiments on a dataset of 160 mobile applications show that KZGNN outperforms nine state-of-the-art traffic classification baselines and achieves a 5.2% improvement in identifying unseen application categories, demonstrating its effectiveness for mobile application identification in zero-shot scenarios. Full article

Parkinson’s Disease (PD) is a neurodegenerative disorder in which gait abnormalities serve as key indicators of motor impairment and disease progression. Although wearable sensor-based gait analysis has advanced, existing methods still face challenges in modeling multi-sensor spatial relationships, extracting adaptive multi-scale temporal features, and effectively integrating time–frequency information. To address these issues, this paper proposes a multi-sensor gait neural network that integrates biomechanical priors with time–frequency collaborative learning for the automatic assessment of PD gait severity. The framework consists of three core modules: (1) BGS-GAT (Biomechanics-Guided Graph Attention Network), which constructs a sensor graph based on plantar anatomy and explicitly models inter-regional force dependencies via graph attention; (2) AMS-Inception1D (Adaptive Multi-Scale Inception-1D), which employs dilated convolutions and channel attention to extract multi-scale temporal features adaptively; and (3) TF-Branch (Time–Frequency Branch), which applies Real-valued Fast Fourier Transform (RFFT) and frequency-domain convolution to capture rhythmic and high-frequency components, enabling complementary time–frequency representation. Experiments on the PhysioNet multi-channel foot pressure dataset demonstrate that the proposed model achieves 0.930 in accuracy and 0.925 in F1-score for four-class severity classification, outperforming state-of-the-art deep learning models. Full article

Multi-view learning has recently gained considerable attention in graph representation learning as it enables the fusion of complementary information from multiple views to enhance representation quality. However, most existing studies neglect that irrelevant views may introduce noise and negatively affect representation quality. To address the issue, we propose a novel multi-view representation learning framework called a $\mathbf{Vi}$ew $\mathbf{Fi}$lter-driven graph representation fusion network, named $\mathbf{ViFi}$. Following the “less for better” principle, the framework focuses on filtering informative views while discarding irrelevant ones. Specifically, an entropy-based adaptive view filter was designed to dynamically filter the most informative views by evaluating their feature–topology entropy characteristics, aiming to not only reduce irrelevance among views but also enhance their complementarity. In addition, to promote more effective fusion of informative views, we propose an optimized fusion mechanism that leverages the filtered views to identify the optimal integration strategy using a novel information gain function. Through extensive experiments on classification and clustering tasks, ViFi demonstrates clear performance advantages over existing state-of-the-art approaches. Full article

This study explores how adolescent learners conceptualize the emotion of love in their first language (Spanish) and in English as a foreign language (EFL), comparing monolingual Spanish speakers and Spanish–Arabic bilinguals. A total of 66 participants (33 per group), all with A2 proficiency in English, completed a semantic fluency task in both Spanish and English, producing as many words as possible in relation to the prompts Amor and Love. The data were analyzed using graph theory to capture the organization of participants’ emotion lexicons. The results show that love is a highly productive and cohesive semantic field, eliciting significantly more responses in L1 than in L2, for both Spanish-only (t = −8.866, p < 0.001) and Spanish–Arabic (W = 101.0, p = 0.001) participants. The differences between the two learner cohorts were not significant in Spanish nor in English. The results from the graph analyses revealed that learners displayed rich and strongly connected networks in Spanish, with learners with a migration origin showing slightly more fragmented networks. In English, both groups performed similarly, with responses probably mediated by L1 translation equivalents and metaphorical associations (e.g., heart, flower, and red). The findings suggest that emotional lexicons are better developed and more efficiently organized in the L1, whereas FL representations are shaped by proficiency, context of learning, and reliance on L1 conceptual structures. This study contributes novel insights into bilingual and heritage learners’ emotional conceptualization and highlights the value of graph analysis for examining the structure of emotion words. Full article

Session-based recommender systems (SBRs) are critically impaired by exposure bias in observational training logs, causing models to overfit to logging policies rather than true user preferences. This bias distorts offline evaluation and harms generalization, particularly for long-tail items. To address this, we propose the Propensity- and Temporal-consistency Enhanced Graph Transformer (PTE-GT), a principled framework that enhances a recent interval-aware graph transformer backbone with two synergistic training-time modules. This Graph Neural Network -based architecture is adept at modeling the complex, graph-structured nature of session data, capturing intricate item transitions that sequential models might miss. First, we introduce a propensity-aware (PA) optimization objective based on the self-normalized inverse propensity scoring (SNIPS) estimator. This module leverages logs containing randomized exposure or logged behavior-policy propensities to learn an unbiased risk estimate, correcting for the biased data distribution. Second, we design a lightweight, view-free temporal consistency (TC) contrastive regularizer that enforces alignment between session prefixes and suffixes, improving representation robustness without computationally expensive graph augmentations, which are often a bottleneck for graph-based contrastive methods. We conduct comprehensive evaluations on three public session-based benchmarks—KuaiRand, the OTTO e-commerce challenge dataset (OTTO), and the YOOCHOOSE-1/64 split (YOOCHOOSE)—and additionally on the publicly available Open Bandit Dataset (OBD) containing logged bandit propensities. Our results demonstrate that PTE-GT significantly outperforms strong baselines. Critically, on datasets with randomized exposure or logged propensities, our unbiased evaluation protocol, using SNIPS-weighted metrics, reveals a substantial performance leap that is masked by standard, biased metrics. Our method also shows marked improvements in model calibration and long-tail item recommendation. Full article

Aerial situational awareness (SA) faces significant challenges due to inherent complexity involving large-scale dynamic entities and intricate spatio-temporal relationships. While deep learning advances SA for specific data modalities (static or time-series), existing approaches often lack the holistic, vision-centric perspective essential for human decision-making. To bridge this gap, we propose a unified GNN-CV framework for operational-level SA. This framework leverages mature computer vision (CV) architectures to intelligently process radar-map-like representations, addressing diverse SA tasks within a unified paradigm. Key innovations include methods for sparse entity attribute transformation graph neural networks (SET-GNNs), large-scale radar map reconstruction, integrated feature extraction, specialized two-stage pre-training, and adaptable downstream task networks. We rigorously evaluate the framework on critical operational-level tasks: aerial swarm partitioning and configuration recognition. The framework achieves an impressive end-to-end recognition accuracy exceeding 90.1%. Notably, in specialized tactical scenarios featuring small, large, and irregular flight intervals within formations, configuration recognition accuracy surpasses 85.0%. Even in the presence of significant position and heading disturbances, accuracy remains above 80.4%, with millisecond response cycles. Experimental results highlight the benefits of leveraging mature CV techniques such as image classification, object detection, and image generation, which enhance the efficacy, resilience, and coherence of intelligent situational awareness. Full article

RNA has emerged as a critical drug target, and accurate prediction of its binding affinity with small molecules is essential for the design and screening of RNA-targeted therapeutics. Although current deep learning methods have achieved progress in predicting RNA–small molecule interactions, existing models commonly suffer from reliance on single-modality features and insufficient representation of cross-level interactions. This paper proposes a multi-level cross-modal attention fusion framework, named MCARSMA, which integrates sequence, structural, and semantic information from both RNA and small molecules. The model employs a dual-path interaction mechanism to capture multi-scale relationships spanning from atom–nucleotide fine-grained interactions to global conformational features. The model architecture comprises (1) the feature extraction of RNA secondary structure and sequence using GAT and CNN; (2) small molecule representation that combines GCN and Transformer for joint graph and sequence embedding; (3) a dual-path fusion module for atom–nucleotide fine-grained interactions and structure-guided multi-level interactions; and (4) an adaptive feature weighting mechanism implemented via a gated network. The results demonstrate that on the R-SIM dataset, MCARSMA achieves RMSE = 0.883, PCC = 0.772, and SCC = 0.773, validating the effectiveness of the proposed multi-level cross-modal attention fusion framework. This study provides a highly interpretable deep learning solution with high predictive accuracy. Full article

Spatiotemporal traffic flow prediction is a fundamental task in intelligent transportation systems and is crucial for promoting efficient and sustainable urban mobility, especially under increasingly complex and rapidly evolving traffic conditions. To overcome the challenges of modeling high-order spatial dependencies and heterogeneous temporal patterns, this study develops a novel Hierarchical Spatiotemporal Graph–Hypergraph Network (HSTGHN). For spatial representation learning, a hypergraph neural module is employed to capture high-order interactions across the road network, while a hypernode mechanism is designed to characterize complex correlations among multiple road segments. Furthermore, an adaptive adjacency matrix is constructed in a data-driven manner and enriched with prior knowledge of bidirectional traffic flows, thereby enhancing the robustness and accuracy of graph structural representations. For temporal modeling, HSTGHN integrates the complementary strengths of Gated Recurrent Units (GRUs) and Transformers: GRUs effectively capture local sequential dependencies, whereas Transformers excel at modeling global dynamic patterns. This joint mechanism enables comprehensive learning of both short-term and long-term temporal dependencies. Extensive experiments on multiple benchmark datasets demonstrate that HSTGHN consistently outperforms state-of-the-art baselines in terms of prediction accuracy and stability, with particularly significant improvements in long-term forecasting and highly dynamic traffic scenarios. These improvements provide more reliable decision support for intelligent transportation systems, contributing to enhanced traffic efficiency, reduced congestion, and ultimately more sustainable urban mobility. Full article

Single-cell RNA sequencing (scRNA-seq) provides a high-resolution view of cellular heterogeneity, yet accurate cell-type annotation remains challenging due to data sparsity, technical noise, and variability across tissues, platforms, and species. Many existing annotation tools depend on a single form of prior knowledge, such as marker genes or reference profiles, which can limit performance when these resources are incomplete or inconsistent. Here, we present scANMF, a prior- and graph-regularized non-negative matrix factorization framework that integrates marker-gene information, partial label supervision, and the local manifold structure into a unified annotation model. scANMF factorizes the expression matrix into interpretable gene–factor and cell–factor representations, enabling accurate annotation in settings with limited or noisy prior information. Across multiple real scRNA-seq collections, scANMF achieved a high annotation accuracy in within-dataset, cross-platform, and cross-species evaluations. The method remained stable under varying levels of label sparsity and marker-gene noise and showed a broad robustness to hyperparameter choices. Ablation analyses indicated that marker priors, label supervision, and graph regularization contribute complementary information to the overall performance. These results support scANMF as a practical and robust framework for single-cell annotation, particularly in applications where high-quality prior knowledge is restricted. Full article

Accurate group target association is essential for multi-sensor multi-target tracking, particularly in heterogeneous radar systems where systematic biases, asynchronous observations, and dense formations frequently cause ambiguous or incorrect associations. Existing approaches often rely on strict spatial assumptions or pre-trained models, limiting their robustness when measurement distortions and sensor-specific deviations are present. To address these challenges, this work proposes a robust association framework that integrates deep feature embedding, density-adaptive clustering, and global graph-theoretic matching. The method first applies an autoencoder–HDBSCAN clustering scheme to extract stable latent representations and obtain adaptive group structures under nonlinear distortions and non-uniform target densities. A weighted bipartite graph is then constructed, and a global optimal matching strategy is employed to compensate for heterogeneous systematic errors while preserving inter-group structural consistency. A mutual-support verification mechanism further enhances robustness against random disturbances. Monte Carlo experiments show that the proposed method maintains over 90% association accuracy even in dense scenarios with a target spacing of 1.4 km. Under various systematic bias conditions, it outperforms representative baselines such as Deep Association and JPDA by more than 20%. These results demonstrate the method’s robustness, adaptability, and suitability for practical multi-radar applications. The framework is training-free and easily deployable, offering a reliable solution for group target association in real-world multi-sensor fusion systems. Full article

Temporal knowledge graphs (TKGs) incorporate temporal information into traditional triplets, enhancing the dynamic representation of real-world events. Temporal knowledge graph reasoning aims to infer unknown quadruples at future timestamps through dynamic modeling and learning of nodes and edges in the knowledge graph. Existing TKG reasoning approaches often suffer from two main limitations: neglecting the influence of temporal information during entity embedding and insufficient or unreasonable processing of relational structures. To address these issues, we propose DERP, a relation-aware reasoning model with dynamic evolution mechanisms. The model enhances entity embeddings by jointly encoding time-varying and static features. It processes graph-structured data through relational graph convolutional layers, which effectively capture complex relational patterns between entities. Notably, it introduces an innovative relational-aware attention mechanism (RAGAT) that dynamically adapts the importance weights of relations between entities. This facilitates enhanced information aggregation from neighboring nodes and strengthens the model’s ability to capture local structural features. Subsequently, prediction scores are generated utilizing a convolutional decoder. The proposed model significantly enhances the accuracy of temporal knowledge graph reasoning and effectively handles dynamically evolving entity relationships. Experimental results on four public datasets demonstrate the model’s superior performance, as evidenced by strong results on standard evaluation metrics, including Mean Reciprocal Rank (MRR), Hits@1, Hits@3, and Hits@10. Full article

Smart contracts are vulnerable to critical, design-level Business Logic Flaws (BLFs) that conventional analysis tools often fail to detect. To address this semantic gap, this study introduces a novel ontological framework that formally models the link between high-level architectural intent and low-level Sui Move code. The methodology employs a rigorous Linked Open Terms (LOT) approach to construct a comprehensive ontology, integrated with a library of secure design patterns and process-aware Object-Centric Dynamic Condition Response (OC-DCR) graphs. Qualitative validation was conducted on four canonical security patterns (Access Control, Circuit Breaker, Time Incentivization, Escapability) drawn from the official Sui Framework, confirming the framework’s representational adequacy and logical consistency. Ultimately, this work contributes the first machine-readable semantic layer for Sui Move, decoupling reasoning from raw code availability, and providing the essential semantic foundation for the future development of pattern-aware auditing tools. Full article

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. Full article

The demand for real-time land cover mapping from high-resolution remote sensing (HR-RS) imagery motivates lightweight segmentation models running directly on satellites. By processing on-board and transmitting only fine-grained semantic products instead of massive raw imagery, these models provide timely support for disaster response, environmental monitoring, and precision agriculture. Many recent methods combine convolutional neural networks (CNNs) with Transformers to balance local and global feature modeling, with convolutions as explicit information aggregation modules. Such heterogeneous hybrids may be unnecessary for lightweight models if similar aggregation can be achieved homogeneously, and operator inconsistency complicates optimization and hinders deployment on resource-constrained satellites. Meanwhile, lightweight Transformer components in these architectures often adopt aggressive channel compression and shallow contextual interaction to meet compute budgets, impairing boundary delineation and recognition of small or rare classes. To address this, we propose SatViT-Seg, a lightweight semantic segmentation model with a pure Vision Transformer (ViT) backbone. Unlike CNN-Transformer hybrids, SatViT-Seg adopts a homogeneous two-module design: a Local-Global Aggregation and Distribution (LGAD) module that uses window self-attention for local modeling and dynamically pooled global tokens with linear attention for long-range interaction, and a Bi-dimensional Attentive Feed-Forward Network (FFN) that enhances representation learning by modulating channel and spatial attention. This unified design overcomes common lightweight ViT issues such as channel compression and weak spatial correlation modeling. SatViT-Seg is implemented and evaluated in LuoJiaNET and PyTorch; comparative experiments with existing methods are run in PyTorch with unified training and data preprocessing for fairness, while the LuoJiaNET implementation highlights deployment-oriented efficiency on a graph-compiled runtime. Compared with the strongest baseline, SatViT-Seg improves mIoU by up to 1.81% while maintaining the lowest FLOPs among all methods. These results indicate that homogeneous Transformers offer strong potential for resource-constrained, on-board real-time land cover mapping in satellite missions. Full article