graph neural networks

MagGAT: Structure-Aware Spatiotemporal Graph Attention for Motor-Induced Magnetic Interference Compensation in Quadruped Robots

Permanent-magnet synchronous motors enable precise motion control in compact robots, but their leakage fields can corrupt onboard magnetometer measurements. Physics-based compensation is effective under fixed geometric conditions, whereas quadruped locomotion continuously changes the motor–sensor relationship. We propo...

Decoding spatial mTOR signalling reveals distinct roles in the tumour microenvironment

Abstract The tumour microenvironment comprises a variety of cell types that interact with malignant cells, influencing both cancer progression and the patient response to therapy. Given the intricate interactions among these components, assessing how signalling pathways contribute to cancer progression by acting on dif...

RMGAT: a Relational Multi-Scale Graph Attention Network for spatial transcriptomics domain identification with systematic component ablation

A systematic ablation study providing evidence-based design guidance for spatial transcriptomics GNNs is provided, with findings support using GAT attention and contrastive learning and investing in node feature quality over edge feature complexity.

Navigating the Polycrisis

Developing economies are particularly prone to polycrisis risk given their inherent fragilities, volatile capital flows, and exposure to geopolitical events. The financial risk methodologies, such as value at risk modeling and linear econometric forecasting, cannot accommodate nonlinear risk interactions across differe...

Learning to Route On-Chip: A Survey of Machine Learning-Based Routing in Networks-on-Chip and Its Hardware Overheads

This survey reviews machine-learning-based NoC routing across a 48-study evidence base, and identifies three recurring gaps: limited scalability beyond small meshes, missing deadlock-freedom guarantees for learned policies, and over-reliance on synthetic traffic.

HAD-MSF: Multi-domain neural fusion with state-space and graph modeling for hyperspectral anomaly detection.

Hyperspectral anomaly detection (HAD) remains challenging because spatial, spectral, and frequency dependencies coexist and exhibit heterogeneous characteristics. Existing CNN-, Transformer-, and GCN-based approaches often rely on a single modeling paradigm, which may limit their ability to fully exploit these compleme...

Tri-branch spatio-temporal learning network with dendritic aggregation based dynamic GCN for multi-lead ECG classification

Electrocardiogram (ECG) is a widely used non-invasive diagnostic tool for cardiovascular disease detection. Its complex spatio-temporal properties pose challenges for effective representation learning. Existing methods mainly focus on spatio-temporal information extraction, but generally ignore the cooperative relation...

Operating-environment risk identification for dangerous goods transport vehicles based on unsafe driving behaviors

OBJECTIVE: Operating environments, including road infrastructure, traffic flow, weather conditions, and mileage, directly influence driving behavior. Because driving behavior ultimately determines road traffic safety, it is critical to determine whether operating environments create conditions that may induce unsafe dr...

Distinct neural networks for experiential and descriptive representations of natural hazard risk

Environmental risks are communicated through experiential formats, such as pictures, videos, and virtual reality simulations, and descriptive formats, such as hazard maps and graphs, yet the neural systems engaged by these formats remain unclear. We acquired functional magnetic resonance imaging data from 45 healthy ad...

Field-validated climate-resilient HVAC control for mixed-use buildings in a hot-arid region

Buildings in desert cities are difficult to operate efficiently because heat waves and airborne dust increase cooling demand, alter short-term thermal behavior, and reduce HVAC efficiency. This study develops and field-validates an adaptive control framework for mixed residential and commercial buildings in a hot-arid...

Node importance evaluation in complex networks based on graph neural networks: A systematic review

A Label-Adaptive Contrastive Loss-Based Deep Hashing Method for Timely and Accurate Traffic Metadata Retrieval

With the rapid development of the Internet of Things (IoT), the volume of network traffic data has increased exponentially. The high-dimensional, heterogeneous nature of such data makes efficient retrieval increasingly challenging, thereby degrading the performance of traffic processing systems. To address the ineffici...