Search Results (294)

Binding affinity prediction in computational drug discovery is confounded by trivial correlations between molecular size and measured potency. We introduce cellular sheaf Laplacians as descriptors of ligand molecular geometry that quantify geometric frustration independent of system size. Sheaves are constructed over molecular graphs by assigning three-dimensional coordinate spaces to atoms and projection operators encoding ideal bonding geometry to edges; eigendecomposition of the resulting Laplacian yields spectral features measuring inconsistencies between local geometric constraints and global topology. Applied to 14,050 protein-ligand complexes from the PDBbind v2020 refined set, MW-residualized Sheaf features capture a statistically significant geometric signal ($r_{\mathrm{partial}} = 0.171$, $p<{10}^{-70}$) that is orthogonal to the Wiener index ($r=0.013$) and persists after controlling for both molecular weight and classical graph-theoretic descriptors ($r_{\mathrm{partial}} = 0.390$, $p<{10}^{-9}$). Sheaf spectral features alone achieve predictive performance ($R^2=0.403$) approaching that of fourteen classical cheminformatics descriptors ($R^2=0.446$), and their combination yields consistent improvements across the binding affinity spectrum (RMSE $=1.43$$p{K}_d$). Permutation importance analysis confirms the Sheaf Frobenius norm as the second most influential descriptor after molecular weight. We introduce Topological Binding Efficiency as a size-normalized quality metric identifying ligands that achieve potent binding through geometric complementarity rather than molecular bulk. Gaussian mixture analysis of the maximum eigenvalue distribution among strong binders reveals two distinct spectral modes corresponding to planar aromatic and three-dimensional sp3-rich scaffolds, confirmed by significant differences in fraction of sp3 carbons and aromatic ring counts ($p<{10}^{-8}$). As an intentionally ligand-centric framework, our approach complements rather than replaces protein-aware co-modelling architectures. This work establishes cellular sheaf theory as a principled framework for encoding molecular topology with statistically significant associations with binding affinity, providing interpretable geometric insights that are inaccessible to conventional molecular descriptors. Full article

Accurate measurement of ocean wave parameters is paramount for offshore engineering design and marine environmental monitoring. Distributed pressure sensing technology provides a robust data foundation for analyzing the spatio-temporal characteristics of wave fields through synchronized observations at multiple stations. However, multi-sensor data exhibit high-dimensional spatio-temporal coupling, posing significant challenges for traditional single-point signal processing methods in capturing the topological associations between measurement sites. To address these limitations, this study develops a framework for spatio-temporal feature modeling and wave height reconstruction based on Graph Neural Networks (GNNs). The proposed framework integrates the spatial configuration of sensor arrays with graph-theoretic topological representations. By fusing geometric distances and signal correlations, an adaptive adjacency matrix is constructed to establish a dynamically adjustable graph structure. On the feature extraction level, a spatio-temporal fusion method combining multi-scale graph convolutions and gated temporal modeling is proposed. The experimental results obtained on the Blancs Sablons Bay multi-sensor dataset demonstrate that the proposed method significantly outperforms traditional approaches, achieving lower prediction errors and validating the effectiveness of graph-structured modeling in distributed wave sensing. Full article

Trust decay in social media is a serious threat to user experience and platform ecology. To solve this problem, this paper focuses on triadic closure in the infrastructure of social networks and explores its mechanism in trust decay prevention. Based on the systematic comparison of the ER random graph, the BA scale-free network, a forest fire model, and complete graph approaches, two core metrics, the trust decay risk index and trust resilience index, are proposed in this paper. Combined with structural indices such as the clustering coefficient, the average path length, and the triangular closure number and its growth rate, the quantitative relationship between network structure evolution and trust decay risk is established. It is found that the forest fire model exhibits optimal trust resilience in structure due to its power-law growth characteristics of high clustering, short path length and triangular closure; the dynamic mechanism of trust decay under different network growth modes is significantly different. The validity of the theoretical framework is further supported by the verification of Sina Weibo attention relationship network data. The analysis framework of network growth evolution based on fusion triangle closure and the risk and resilience indicators defined in this paper provides a computable theoretical tool for understanding and predicting trust evolution in social media from the perspective of network structure. Full article

Kolmogorov–Arnold Networks (KANs) have recently gained increasing attention as an alternative to conventional neural architectures, mainly because they replace fixed activation functions with learnable univariate mappings defined along network edges. This design not only increases modeling flexibility but also makes it easier to interpret how inputs are transformed within the network while maintaining parameter efficiency. KANs are particularly well suited for sensor-driven systems where transparency, robustness, and computational constraints are critical. This study provides a survey of KAN-based approaches for processing sensor data. A literature review conducted from 2024 to 2026 examined the deployment of KAN models in industrial and mechanical sensing, medical and biomedical sensing, and remote sensing and environmental monitoring, utilizing a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-based methodology. We first revisit the theoretical foundations of KANs and their main architectural variants, including spline-based, polynomial-based, monotonic, and hybrid formulations, to structure the discussion. From a practical standpoint, we then examine how KAN modules are integrated into modern deep learning pipelines, such as convolutional, recurrent, transformer-based, graph-based, and physics-informed architectures. KAN-based models demonstrate comparable predictive performance as conventional machine learning models, while having fewer parameters and more interpretable representations. Several limitations persist, including computational overhead, sensitivity to noisy signals, and resource-constrained device deployment challenges. Real-world sensor systems encounter significant challenges in adopting KAN-based models, including scalability in large-scale sensor networks, integration with hardware architectures, automated model development, resilience to out-of-distribution conditions, and the need for standardized evaluation metrics. Collectively, these observations provide a clearer understanding of the current and potential limitations of KAN-based models, offering practical guidance on the development of interpretable and efficient learning systems for future sensor equipment applications. Full article

Subgraph isomorphism counting is a fundamental yet computationally challenging task in graph analysis, with broad applications in bioinformatics and social network mining. With the tightening of data privacy regulations and the emergence of data silos, traditional centralized Graph Neural Network (GNN) approaches face significant deployment hurdles. Existing federated subgraph counting methods are primarily designed for database federation scenarios, focusing on exact queries and the privacy and security concerns of databases. However, this rigid focus on exactness and heavy cryptographic security severely limits their scalability and generalizability to complex, arbitrary query patterns. To bridge this gap, we propose a general Federated Edge-Centric Framework for Subgraph Isomorphism Counting (FedCount), shifting the paradigm from exact querying on federated databases to neural approximate counting under federated architectures. Rather than relying on heavy cryptographic techniques, we exclusively leverage the inherent structural isolation of federated learning as a lightweight empirical privacy measure. While this framework does not theoretically defend against advanced gradient-based inference attacks, it successfully prevents the direct leakage of raw graph topology and node features, achieving high-precision approximate counting without the prohibitive cryptographic overheads. Specifically, we introduce two key technical innovations to enhance local counting capability: (1) we integrate a provable edge encoding scheme into the interaction-based GNN architecture, explicitly modeling edge-to-edge interactions to break the expressiveness bottleneck of standard message passing; (2) we design a Residual Edge-Centric Readout mechanism that mitigates the gradient vanishing problem, enabling the effective training of deeper networks to capture high-order topological dependencies. Extensive experiments on multiple benchmark datasets demonstrate that our framework significantly outperforms existing distributed enumeration baselines in terms of generalization and efficiency, approaching the performance of centralized state-of-the-art models. Full article

Traffic flow prediction is a key component of Intelligent Transportation Systems (ITS), crucial for alleviating urban congestion, optimizing traffic management, and improving the overall efficiency of road networks. With the rapid growth in vehicle numbers and the increasing complexity of urban traffic patterns, accurate short-term traffic flow prediction has become increasingly important. This paper comprehensively reviews the latest advancements in traffic flow prediction methods, focusing on graph neural network (GNN)-based approaches and hybrid deep learning frameworks. First, we introduce the fundamental theoretical foundations, including graph neural networks, deep learning algorithms, heuristic optimization methods, and attention mechanisms. Subsequently, we summarize GNN-based prediction methods into four paradigms: (1) federated learning and privacy-preserving methods, enabling cross-regional collaboration while protecting sensitive data; (2) dynamically adaptive graph structure methods, capturing time-varying spatial dependencies; (3) multi-graph fusion and attention mechanism methods, enhancing feature representations from multiple perspectives; and (4) cross-domain technology integration methods, fusing novel architectures and interdisciplinary technologies. Furthermore, we investigate hybrid methods combining signal decomposition, heuristic optimization, and attention mechanisms with LSTM networks to address challenges related to non-stationarity and model optimization. For each category, we analyzed representative works and summarized their core innovations, strengths, and limitations using a systematic comparative table. Finally, we discussed current challenges, including computational complexity, model interpretability, and generalization ability, and outlined future research directions such as lightweight model design, uncertainty quantification, multimodal data fusion, and integration with traffic control systems. This review provides researchers and practitioners with a systematic understanding of the latest advances in traffic flow prediction and offers guidance for methodological selection and future research. Full article

Uncertainty estimation is critical for deploying large language models (LLMs) in safety-sensitive and decision-critical applications. Recent approaches estimate semantic uncertainty by clustering multiple sampled responses into equivalence classes and measuring their diversity via entropy-based criteria. However, existing methods typically rely on greedy hard clustering and von Neumann entropy, which suffer from sensitivity to clustering order, noise in semantic equivalence judgments, and limited control over spectral contributions. In this work, we propose a principled information-theoretic framework for LLM semantic uncertainty estimation based on soft semantic communities and kernel Rényi entropy. Given multiple generations for a query, we construct a weighted semantic graph using pairwise semantic similarity scores and infer soft community assignments via weighted graph community detection. These soft assignments induce a positive semi-definite semantic kernel that captures the distribution of semantic modes without enforcing hard equivalence relations. Uncertainty is then quantified by the Rényi entropy of the kernel spectrum, yielding a tunable measure that interpolates between sensitivity to dominant semantic modes and long-tail semantic diversity. Compared to prior von Neumann entropy-based estimators, the proposed Rényi spectral uncertainty offers improved robustness to semantic noise, reduced dependence on clustering heuristics, and greater flexibility through its order parameter. Extensive experiments on question answering tasks demonstrate that our method provides more stable and discriminative uncertainty estimates, particularly under limited sampling budgets and noisy semantic judgments. Full article

A graph-theoretical approach to the analysis of motion and rest in many-body systems is developed. Point bodies are represented as vertices of a complete bi-colored graph, termed the motion–rest graph (MRG). Two vertices are connected by a rust-colored edge when the corresponding bodies are at rest relative to each other; that is, when their mutual distance remains constant in time, bodies moving relative to each other are connected by a cyan edge. It is shown that the logical structure of the relation “to be at rest relative to each other” determines the combinatorial structure of the graph. For one-dimensional motion in classical mechanics and special relativity, this relation is reflexive, symmetric, and transitive, and therefore defines an equivalence relation. As a result, rust edges form disjoint complete cliques corresponding to rest-clusters, and the MRG becomes a semi-transitive complete bi-colored graph that is completely determined by the partition of the bodies into equivalence classes. It is proven that any such graph on five vertices necessarily contains a monochromatic triangle. For two- and three-dimensional motion, the transitivity of relative rest generally fails because constant mutual distance does not imply an equality of velocities in the presence of rotational degrees of freedom. In this case, the MRG is non-transitive, and the Ramsey threshold becomes the classical value R(3,3) = 6. The approach is extended to mixed sets containing moving bodies and reference points, including the center of mass of the system. Generalizations to general relativity and quantum mechanics are also discussed. In general relativity, transitivity of relative rest is generically lost because global rigid congruences do not generally exist. In quantum mechanics, exact transitivity survives only at the level of idealized delocalized eigenstates, whereas for physically realizable localized states, the notion of mutual rest becomes only approximate. The results demonstrate that the interplay between kinematics, logical properties of relational motion, and Ramsey-type combinatorial constraints gives rise to unavoidable ordered substructures in many-body systems. Full article

Objective biomarkers for neurodevelopmental disorders remain an unmet clinical need. The electroretinogram (ERG), a non-invasive recording of the retinal response to light, has shown promise as a physiological marker for autism spectrum disorder (ASD) and attention deficit/hyperactivity disorder (ADHD), yet existing classification approaches based on time-domain and time–frequency features achieve limited accuracy in clinically relevant multi-group scenarios. This study introduces ERG-Graph, a novel graph signal processing (GSP) framework that transforms each ERG waveform into a weighted, undirected graph through amplitude quantization and temporal-adjacency connectivity. Nine topological and spectral features, including total load centrality, clique number, algebraic connectivity, and clustering coefficient, were extracted from each graph to characterize the structural dynamics of the signal. Using light-adapted ERG recordings from 278 participants (ASD = 77, ADHD = 43, ASD + ADHD = 21, Control = 137), we evaluated these features across binary, three-group, and four-group classification scenarios using seven machine learning classifiers with 10-fold subject-wise cross-validation. The proposed ERG-Graph features achieved balanced accuracies of 0.91 (ASD vs. control, males) and 0.88 (ADHD vs. control, females). Critically, fusing ERG-Graph with time-domain features yielded a balanced accuracy of 0.81 for three-group classification (ASD vs. ADHD vs. control), representing an 11-percentage-point improvement over the previous benchmark of 0.70. Statistical analysis confirmed significant topological differences between groups (Kruskal–Wallis, p < 0.001; Cliff’s delta: large effect sizes), and SHAP analysis revealed that graph-theoretic features dominated the top-ranked predictors. These results demonstrate that graph-based topological features capture discriminative information in the ERG waveform that is inaccessible to conventional signal analysis methods, advancing the development of objective biomarkers for neurodevelopmental disorder screening. Full article

This article presents a systematic bibliometric analysis on academic research into Artificial Intelligence (AI) applications in Architectural Conceptual Design (ACD). Based on a curated selection of publications indexed in the Web of Science (WoS) and Scopus databases between 2010 and 2025, this article shows a study that maps the intellectual evolution, thematic composition, and methodological trends of the field. By using the software tool VOSviewer, this study generates a series of knowledge graphs, including Keyword Co-Occurrence and International Collaboration Networks. The findings from this study reveal a rapid acceleration in AI-related research focused on the conceptual design stage, highlighting its transformative potential for architectural practice. Through a critical analysis of bibliometric results, this study identifies dominant research emphases, emerging directions, and persistent frictions between academic approaches and industry adoption. This review article contributes to the theoretical consolidation of AI applications in ACD and provides a structured foundation for future ACD-related research and practice. Full article

Multi-agent swarm collaboration, inspired by the collective behaviors of biological swarms in nature, has wide applications in dynamic open environments. However, hybrid action spaces in multi-agent reinforcement learning (MARL) present a critical challenge: the inherent coupling between discrete and continuous actions severely undermines policy stability and convergence, especially under dynamic topologies. Existing methods fail to decouple this coupling, leading to suboptimal policies and unstable training. This paper addresses the core problem of action coupling under dynamic topologies, proposing a Parametrized Graph Convolution Reinforcement Learning (P-DGN) method. Operating within the actor–critic framework, P-DGN decouples the optimization pathways for hybrid actions, with a biomimetic observation design inspired by starling flock behaviors: each agent only observes the states of its seven nearest neighbors to achieve efficient local interaction and global collaboration. Its actor network uses multi-head attention to build dynamic relation kernels, develops temporal relation regularization (TRR) to improve policy consistency across time steps, and generates continuous actions with a Gaussian policy. Meanwhile, P-DGN’s critic network, based on deep Q-network (DQN), evaluates Q-values for discrete actions to guide optimal choices. We evaluate P-DGN in two different multi-agent cooperative environments. Experimental results show that compared with parametrized deep Q-network (P-DQN) and DQN baseline, the proposed method has faster convergence speed and stronger training stability. Moreover, with dense rewards, P-DGN agents learn emergent tactics like encirclement. Overall, P-DGN offers a new approach for optimizing hybrid action spaces in multi-agent systems within open, dynamic environments, balancing theoretical generality with practical utility, and its biomimetic design provides a biologically plausible framework for multi-agent swarm collaboration. Full article

Conventional methods for calculating sortie mission reliability of shipborne vehicle layouts suffer from excessive computational overhead, long runtimes, and large labeled data requirements. To address these limitations, this work proposes a specialized graph neural network architecture tailored for limited-data small-sample scenarios, denoted as the Small-Sample Graph Neural Network (SS-GNN). The proposed SS-GNN integrates multi-relational graph convolutional layers, an adaptive attention weighting mechanism, small-sample regularization techniques, and an uncertainty quantification module to accurately capture the heterogeneous multidimensional dependencies between vehicles. To further improve learning performance under data-scarce conditions, we employ a hybrid training strategy combining meta-learning-based pretraining, contrastive learning for representation enhancement, knowledge distillation, and transfer learning. Experimental results demonstrate that SS-GNN substantially outperforms traditional reliability calculation methods, classical machine learning models, and state-of-the-art GNN baselines across three key dimensions: predictive accuracy, computational efficiency, and generalization robustness, while also providing theoretically grounded uncertainty estimates for all predictions. This work provides both a theoretical foundation and a practical technical framework for shipborne vehicle reliability prediction and offers a generalizable solution for small-sample graph regression tasks in industrial domains. Future work will focus on extending the approach to extremely low-data regimes via specialized few-shot learning algorithms, incorporating dynamic relation modeling for time-varying sortie processes, and integrating domain knowledge graphs to broaden its operational applicability. Full article

The evolution toward 6G Computing Power Networks (CPN) aims to deeply integrate multi-tier computing resources across Cloud, Edge, and end devices. However, the significant heterogeneity of computing resources, characterized by varying hardware architectures such as CPUs, GPUs, and NPUs, coupled with the time-varying network topology caused by terminal mobility, poses severe challenges to realizing efficient integrated scheduling that satisfies Quality of Service (QoS). To address spatiotemporal mismatches between task requirements and hardware architectures, this paper proposes an integrated scheduling method combining Discrete Time-Varying Graph (DTVG) construction with Multi-Agent Reinforcement Learning (MARL). Specifically, we model the dynamic interaction between mobile tasks and heterogeneous nodes as a DTVG to capture spatiotemporal evolution and employ a QMIX-based algorithm to enable collaborative decision-making among distributed agents. Simulation results demonstrate that the proposed approach effectively solves the joint optimization problem of heterogeneous resource matching and dynamic path planning, significantly outperforming traditional baselines in terms of resource utilization and average latency. This study confirms that incorporating graph-theoretic modeling with reinforcement learning offers a robust solution for the complex coupling of communication and computation in dynamic 6G networks. Full article

Topological graph theory provides a quantitative approach to understanding the structural complexities of sulfonamide compounds, which are prominent for their therapeutic importance in cancer treatment. A new computational scheme to predict the physicochemical and biological functions of sulfonamide derivatives, based on connection numbers and connection-based topological indices as alternatives to the theoretically overt degree-based index, is proposed. A set of structurally diverse sulfonamide compounds as chemical graphs is considered, and the relevant graph descriptors are computed using different connection numbers. Due to the complexity of the calculations involved in connectivity and other such indices, algorithms were developed in Python 3.12.12 to automate the extraction and calculation of these indices. QSPR analysis, with the help of supervised machine learning models like linear regression, among others, and various statistical techniques, was employed to obtain insight into the relationships existing between the structural properties and the molecular properties measured, such as melting point, molecular weight, etc. These results demonstrate the great predictive capability of connection-based indices in assessing pharmacologic efficacy or molecular behavior. The holistic setting thus links topological modeling to data-driven prediction and provides a window into the rational design and optimization of sulfonamide-based cancer therapeutics. Full article

A comprehensive analysis of three graph-theoretic path planning algorithms designed for multi-robotic systems (MRS) was undertaken. The algorithms were the multi-robot path planning algorithm (MRPP), central algorithm (CA), and the optimisation central algorithm (OCA). The primary objective of these algorithms is to enhance path optimality, mitigate computational complexity, and ensure robust inter-robot collision avoidance. The MRPP is a composite approach integrating the visibility graph (VG) for path generation. The CA, derived from VG principles, utilises a central baseline (CB) approach to reduce vertex count, thereby decreasing computational cost while maintaining path efficiency. The OCA extends CA by integrating obstacle expansion and safety margins to enhance collision avoidance and path optimisation. Comparative analysis through simulations in 2D polygonal environments compared the performance of these algorithms, considering their computational efficiency, path optimisation, and collision avoidance. CA and OCA demonstrated significant improvement over the VG-based approach, especially concerning optimality and optimisation. CA reduced the average path length by 4.3% compared with MRPP, while OCA achieved a 6.8% reduction over MRPP, and 2.5% over CA, demonstrating its superior balance between optimality and efficiency. MRPP offers robust connectivity, making it preferable in scenarios where communication is critical. The study’s findings assist in devising MPRPP solutions. Full article