Search Results (66)

Network robustness optimization is crucial for enhancing the resilience of industrial networks and social systems against malicious attacks. Existing studies typically evaluate the robustness by simulating the sequential removal of nodes or edges and recording the residual connectivity at each step. However, the attack simulation is computationally expensive and becomes impractical for large-scale networks. Therefore, this paper proposes a multiobjective evolutionary algorithm assisted by a graph isomorphism network (GIN)-based surrogate model to efficiently optimize network robustness. First, the robustness optimization task is formulated as a multiobjective problem that simultaneously considers network robustness against attacks and the structural modification cost. Then, a GIN-based surrogate model is constructed to approximate the robustness, replacing the expensive simulation assessments. Finally, the multiobjective evolutionary algorithm is employed to explore promising network structures guided by the surrogate model, which is continuously updated via online learning to improve both prediction accuracy and optimization performance. Experimental results in various synthetic and real-world networks demonstrate that the proposed algorithm reduces the computational cost of the robustness evaluation by about $65\%$ while achieving comparable or even superior robustness optimization performance compared with those of baseline algorithms. These results indicate that the proposed method is practical and scalable and can be applied to enhance the robustness of industrial and social networks. Full article

Molecular simulation is central to modern drug discovery but is often limited by high computational cost and the complexity of molecular interactions. Deep-learning drug–target interaction (DTI) prediction can accelerate screening; however, many models underuse the local functional structure features—binding motifs, reactive groups, and residue-level fragments—that drive recognition. We present LoF-DTI, a framework that explicitly represents and couples such local features. Drugs are converted from SMILES into molecular graphs and targets from sequences into feature representations. On the drug side, a Jumping Knowledge (JK) enhanced Graph Isomorphism Network (GIN) extracts atom- and neighborhood-level patterns; on the target side, residual CNN blocks with progressively enlarged receptive fields, augmented by N-mer substructural statistics, capture multi-scale local motifs. A Gated Cross-Attention (GCA) module then performs atom-to-residue interaction learning, highlighting decisive local pairs and providing token-level interpretability through attention scores. By prioritizing locality during both encoding and interaction, LoF-DTI delivers competitive results across multiple benchmarks and improves early retrieval relevant to virtual screening. Case analyses show that the model recovers known functional binding sites, suggesting strong potential to provide mechanism-aware guidance for molecular simulation and to streamline the drug design pipeline. Full article

This paper introduces KG-FLoc, a knowledge graph-enhanced framework for secondary circuit fault localization in intelligent substations. The proposed KG-FLoc innovatively formalizes secondary components (e.g., circuit breakers, disconnectors) as graph nodes and their multi-dimensional relationships (e.g., electrical connections, control logic) as edges, constructing the first comprehensive knowledge graph (KG) to structurally and operationally model secondary circuits. By reframing fault localization as a knowledge graph link prediction task, KG-FLoc identifies missing or abnormal connections (edges) as fault indicators. To address dynamic topologies and sparse fault samples, KG-FLoc integrates two core innovations: (1) a relation-aware gated unit (RGU) that dynamically regulates information flow through adaptive gating mechanisms, and (2) a hierarchical graph isomorphism network (GIN) architecture for multi-scale feature extraction. Evaluated on real-world datasets from 110 kV/220 kV substations, KG-FLoc achieves 97.2% accuracy in single-fault scenarios and 93.9% accuracy in triple-fault scenarios, surpassing SVM, RF, MLP, and standard GNN baselines by 12.4–31.6%. Beyond enhancing substation reliability, KG-FLoc establishes a knowledge-aware paradigm for fault diagnosis in industrial systems, enabling precise reasoning over complex interdependencies. Full article

The purpose of few-shot relation extraction (RE) is to recognize the relationship between specific entity pairs in text when there are a limited number of labeled samples. A few-shot RE method based on a prototype network, which constructs relation prototypes by relying on the support set to assign labels to query samples, inherently leverages the symmetry between support and query processing. Although these methods have achieved remarkable results, they still face challenges such as the misjudging of noisy samples or outliers, as well as distinguishing semantic similarity relations. To address the aforementioned challenges, we propose a novel semantic enhanced prototype network, which can integrate the semantic information of relations more effectively to promote more expressive representations of instances and relation prototypes, so as to improve the performance of the few-shot RE. Firstly, we design a prompt encoder to uniformly process different prompt templates for instance and relation information, and then utilize the powerful semantic understanding and generation capabilities of large language models (LLMs) to obtain precise semantic representations of instances, their prototypes, and conceptual prototypes. Secondly, graph attention learning techniques are introduced to effectively extract specific-relation features between conceptual prototypes and isomorphic instances while maintaining structural symmetry. Meanwhile, a prototype-level contrastive learning strategy with bidirectional feature symmetry is proposed to predict query instances by integrating the interpretable features of conceptual prototypes and the intra-class shared features captured by instance prototypes. In addition, a clustering loss function was designed to guide the model to learn a discriminative metric space with improved relational symmetry, effectively improving the accuracy of the model’s relationship recognition. Finally, the experimental results on the FewRel1.0 and FewRel2.0 datasets show that the proposed approach delivers improved performance compared to existing advanced models in the task of few-shot RE. Full article

Two hybrid, entropy-guided node metrics are proposed for the k-hop environment: Entropy-Weighted Redundancy (EWR) and Normalized Entropy Density (NED). The central idea is to couple local Shannon entropy with neighborhood density/redundancy so that structural heterogeneity around a vertex is captured even when classical indices (e.g., degree or clustering) are similar. The metrics are formally defined and shown to be bounded, isomorphism-invariant, and stable under small edge edits. Their behavior is assessed on representative topologies (Erdős–Rényi, Barabási–Albert, Watts–Strogatz, random geometric graphs, and the Zephyr quantum architecture). Across these settings, EWR and NED display predominantly negative correlation with degree and provide information largely orthogonal to standard centralities; vertices with identical degree can differ by factors of two to three in the proposed scores, revealing bridges and heterogeneous regions. These properties indicate utility for vulnerability assessment, topology-aware optimization, and layout heuristics in engineered and quantum networks. Full article

Traditional educational assessment systems suffer from inefficient question selection strategies that fail to optimally probe student knowledge while requiring extensive testing time. We present a novel hierarchical probabilistic neural framework that integrates Bayesian inference with symmetric deep neural architectures to enable adaptive, efficient knowledge assessment. Our method models student knowledge as latent representations within a graph-structured concept dependency network, where probabilistic mastery states, updated through variational inference, are encoded by symmetric graph properties and symmetric concept representations that preserve structural equivalences across similar knowledge configurations. The system employs a symmetric dual-network architecture: a concept embedding network that learns scale-invariant hierarchical knowledge representations from assessment data and a question selection network that optimizes symmetric information gain through deep reinforcement learning with symmetric reward structures. We introduce a novel uncertainty-aware objective function that leverages symmetric uncertainty measures to balance exploration of uncertain knowledge regions with exploitation of informative question patterns. The hierarchical structure captures both fine-grained concept mastery and broader domain understanding through multi-scale graph convolutions that preserve local graph symmetries and global structural invariances. Our symmetric information-theoretic method ensures balanced assessment strategies that maintain diagnostic equivalence across isomorphic concept subgraphs. Experimental validation on large-scale educational datasets demonstrates that our method achieves 76.3% diagnostic accuracy while reducing the question count by 35.1% compared to traditional assessments. The learned concept embeddings reveal interpretable knowledge structures with symmetric dependency patterns that align with pedagogical theory. Our work generalizes across domains and student populations through symmetric transfer learning mechanisms, providing a principled framework for intelligent tutoring systems and adaptive testing platforms. The integration of probabilistic reasoning with symmetric neural pattern recognition offers a robust solution to the fundamental trade-off between assessment efficiency and diagnostic precision in educational technology. Full article

Finding the maximum common induced subgraph is a fundamental problem in computer science. Proven to be NP-hard in the 1970s, it has, nowadays, countless applications that still motivate the search for efficient algorithms and practical heuristics. In this work, we extend a state-of-the-art branch-and-bound exact algorithm with new techniques developed in the deep-learning domain, namely graph neural networks and node embeddings, effectively transforming an efficient yet uninformed depth-first search into an effective best-first search. The change enables the algorithm to find suitable solutions within a limited budget, pushing forward the method’s time efficiency and applicability on larger graphs. We evaluate the usage of the L2 norm of the node embeddings and the Cumulative Cosine Similarity to classify the nodes of the graphs. Our experimental analysis on standard graphs compares our heuristic against the original algorithm and a recently tweaked version that exploits reinforcement learning. The results demonstrate the effectiveness and scalability of the proposed approach, compared with the state-of-the-art algorithms. In particular, this approach results in improved results on over 90% of the larger graphs; this would be more challenging in a constrained industrial scenario. Full article

The design of materials with programmable degradation profiles presents a fundamental challenge in pattern recognition across molecular space, requiring the identification of complex structure–property relationships within an exponentially large chemical domain. This paper introduces a novel physics-informed deep learning framework that integrates multi-scale molecular sensing data with reinforcement learning algorithms to enable intelligent characterization and prediction of polymer degradation dynamics. Our method combines three key innovations: (1) a dual-channel sensing architecture that fuses spectroscopic signatures from Graph Isomorphism Networks with temporal degradation patterns captured by transformer-based models, enabling comprehensive molecular state detection across multiple scales; (2) a physics-constrained policy network that ensures sensor measurements adhere to thermodynamic principles while optimizing the exploration of degradation pathways; and (3) a hierarchical signal processing system that balances multiple sensing modalities through adaptive weighting schemes learned from experimental feedback. The framework employs curriculum-based training that progressively increases molecular complexity, enabling robust detection of degradation markers linking polymer architectures to enzymatic breakdown kinetics. Experimental validation through automated synthesis and in situ characterization of 847 novel polymers demonstrates the framework’s sensing capabilities, achieving a 73.2% synthesis success rate and identifying 42 structures with precisely monitored degradation profiles spanning 6 to 24 months. Learned molecular patterns reveal previously undetected correlations between specific spectroscopic signatures and degradation susceptibility, validated through accelerated aging studies with continuous sensor monitoring. Our results establish that physics-informed constraints significantly improve both the validity (94.7%) and diversity (0.82 Tanimoto distance) of generated molecular structures compared with unconstrained baselines. This work advances the convergence of intelligent sensing technologies and materials science, demonstrating how physics-informed machine learning can enhance real-time monitoring capabilities for next-generation sustainable materials. Full article

Axial piston pumps play a vital role in fluid power systems, which are widely employed in diverse fields such as aerospace, ocean engineering, and rail transit. It is essential to accurately diagnose faults in these pumps since their reliable operation hinges on it. A graph isomorphic network with a spatio-temporal attention mechanism (GIN-ST) is proposed in this paper for fault diagnosis of hydraulic axial piston pumps; GIN-AM addresses the problem of traditional intelligent fault diagnosis methods being limited to nonlinear mapping and transformation in Euclidean space. Initially, the weighted graphs are constructed from a univariate time series through K-nearest neighbor graph methods. Subsequently, a spatio-temporal attention-based module used to learn the graph representation of piston pump faults is presented, where a novel READOUT function and Transformer encoder provide spatial and temporal interpretability, respectively. Finally, the proposed (GIN-ST) model is compared against other intelligent fault diagnosis methods, and the superiority of the proposed method is proven. Full article

The significance of searching for edge crossings in graph theory lies inter alia in enhancing the clarity and readability of graph representations, which is essential for various applications such as network visualization, circuit design, and data representation. This paper focuses on exploring the crossing number of the join product $G^{*}+D_n$, where $G^{*}$ is a graph isomorphic to the path on four vertices $P_4$ with an additional two vertices adjacent to two inner vertices of $P_4$, and $D_n$ is a discrete graph composed of n isolated vertices. The proof is based on exact crossing-number values for join products involving particular subgraphs $H_k$ of $G^{*}$ with discrete graphs $D_n$ combined with the symmetrical properties of graphs. This approach could also be adapted to determine the unknown crossing numbers of two other 6-vertices graphs obtained by adding one or two additional edges to the graph $G^{*}$. Full article

Multi-sensor fault diagnosis, especially when using heterogeneous sensors, substantially enhances the accuracy of fault detection in asynchronous motors operating under high-interference conditions. A critical challenge in multi-sensor fault diagnosis lies in effectively fusing data from different sensors. Deep learning offers a promising solution by transforming multi-sensor data into a unified representation, thereby facilitating robust data fusion. However, existing approaches often fail to fully exploit inter-sensor correlations and inherent prior physical knowledge. To address this limitation, we propose a novel graph neural network-based model that emphasizes graph structure construction for heterogeneous multi-sensor information fusion. Our framework includes (1) a multi-task enhanced autoencoder for node feature extraction, enabling discriminative representation learning, particularly with heterogeneous sensor data; (2) an adjacency matrix builder integrated with physical prior constraints to improve the generalization and robustness of the model; and (3) a graph isomorphism network to derive graph-level representations for fault classification. Our experimental results demonstrate the model’s effectiveness in diagnosing faults, as it achieves superior performance compared to conventional methods on two heterogeneous asynchronous motor datasets. Full article

Adverse drug–drug interactions (DDIs) often arise from cytochrome P450 (CYP450) enzyme inhibition, which is vital for metabolism. The accurate identification of CYP450 inhibitors is crucial, but current machine learning models struggle to assess the importance of key inputs like ligand SMILES and protein sequences, limiting their biological insights. The proposed study developed LiSENCE, an artificial intelligence (AI) framework to identify CYP450 inhibitors. It aimed to enhance prediction accuracy and provide biological insights, improving drug development and patient safety regarding drug–drug interactions: The innovative LiSENCE AI framework comprised four modules: the Ligand Encoder Network (LEN), Sequence Encoder Network (SEN), classification module, and explainability (XAI) module. The LEN and SEN, as deep learning pipelines, extract high-level features from drug ligand strings and CYP protein target sequences, respectively. These features are combined to improve prediction performance, with the XAI module providing biological interpretations. Data were outsourced from three databases: ligand/compound SMILES strings from the PubChem and ChEMBL databases and protein target sequences from the Protein Data Bank (PDB) for five CYP isoforms: 1A2, 2C9, 2C19, 2D6, and 3A4. The model attains an average accuracy of 89.2%, with the LEN and SEN contributing 70.1% and 63.3%, respectively. The evaluation performance records 97.0% AUC, 97.3% specificity, 92.2% sensitivity, 93.8% precision, 83.3% F1-score, and 87.8% MCC. LiSENCE outperforms baseline models in identifying inhibitors, offering valuable interpretability through heatmap analysis, which aids in advancing drug development research. Full article

Drug–target affinity (DTA) prediction is a critical step in virtual screening and significantly accelerates drug development. However, existing deep learning-based methods relying on single-modal representations (e.g., text or graphs) struggle to fully capture the complex interactions between drugs and targets. This study proposes CM-DTA, a cross-modal feature fusion model that integrates drug textual representations and molecular graphs with target protein amino acid sequences and structural graphs, enhancing feature diversity and expressiveness. The model employs the multi-perceptive neighborhood self-attention aggregation strategy to capture first- and second-order neighborhood information, overcoming limitations in graph isomorphism networks (GIN) for structural representation. The experimental results on the Davis and KIBA datasets show that CM-DTA significantly improves the performance of drug–target affinity prediction, achieving higher accuracy and better prediction metrics compared to state-of-the-art (SOTA) models. Full article

Oceans are a major source of clean energy, harnessing the vast and consistent power of waves to generate electricity. Today, they are seen as a vital renewable and clean solution for transitioning to a complete fossil fuel-free future world. To get the most out of ocean wave potential, Wave Energy Converters (WECs) are being used to harness the power of ocean waves into usable electrical energy. To this end, to maximize the power generated from the WECs, two strategies for WEC design improvement and optimal coordination can be considered. Among these, optimal coordination is the more straightforward method to implement. However, most of the recently developed coordination strategies are dynamic-based, encountering challenges as the system’s scale expands and grows larger. Consequently, a novel Graph Isomorphic Network (GIN)-based model is presented in this paper. The proposed model consists of the following five layers: the input graph, two GIN convolutional layers (GIN Conv.1, and 2), a mean pooling layer, and the output layer. The target of total generated power is predicted based on the features of the generated power from each WEC and the related spatial coordinates $\{x_i,y_i\}$. Subsequently, based on the anticipated total power considered by the model, the system enables maximum generation. The model performs spatial coordination analyses to present the optimal coordination for each WEC to achieve the objective of maximizing total generated power. The proposed model is evaluated through several Key Performance Indicators (KPIs), achieving the least number of errors in prediction and optimal coordination performances. Full article

Circular RNAs (circRNAs) have attracted increasing attention for their roles in human diseases, making the prediction of circRNA–disease associations (CDAs) a critical research area for advancing disease diagnosis and treatment. However, traditional experimental methods for exploring CDAs are time-consuming and resource-intensive, while existing computational models often struggle with the sparsity of CDA data and fail to uncover potential associations effectively. To address these challenges, we propose a novel CDA prediction method named the Graph Isomorphism Transformer with Dual-Stream Neural Predictor (GIT-DSP), which leverages knowledge graph technology to address data sparsity and predict CDAs more effectively. Specifically, the model incorporates multiple associations between circRNAs, diseases, and other non-coding RNAs (e.g., lncRNAs, and miRNAs) to construct a multi-source heterogeneous knowledge graph, thereby expanding the scope of CDA exploration. Subsequently, a Graph Isomorphism Transformer model is proposed to fully exploit both local and global association information within the knowledge graph, enabling deeper insights into potential CDAs. Furthermore, a Dual-Stream Neural Predictor is introduced to accurately predict complex circRNA–disease associations in the knowledge graph by integrating dual-stream predictive features. Experimental results demonstrate that GIT-DSP outperforms existing state-of-the-art models, offering valuable insights for precision medicine and disease-related research. Full article