graph neural networks

Enhanced brain tumor detection through spectral domain reconstruction graph neural network with privacy-preserving secure smart healthcare framework

Certifying sparse node-feature robustness of graph neural networks via double-sampling randomized smoothing

Multi-instrument music score transcription, symbolic generation, and harmony analysis based on multi-scale residual neural networks

The results demonstrate that the contribution lies in music-specific cross-module coupling and constrained symbolic reconstruction rather than in introducing residual, graph, recurrent, or dilated convolution as isolated operators.

A unified framework for potency-oriented AMP discovery via multi-modal learning and guided sequence synthesis

The generation-screening-validation workflow enables reliable discovery of potent AMPs, and provides a practical strategy for rational peptide design, rapid prediction, and translational applications.

An Integration of Fuzzy-Enhanced Heterophilic Graph Representation Learning for Improving Performance of Link Prediction

Extensive experiments ensure that FHGE consistently outperforms state-of-the-art baselines and demonstrate the power of fuzzy-driven learning in improving graph embedding quality and establish FHGE as a promising solution for real-world link prediction tasks.

Physics-informed graph neural networks for sim-to-real structural response prediction

Physics-informed graph neural networks for forecasting eVTOL-induced traffic state perturbations in real-world road networks

Reaction-Condition- and Ensemble-Aware Screening of Dual-Atom ORR Catalysts via Physics-Informed Machine Learning

A scalable ML-assisted paradigm for realistic electrocatalyst screening is established and design principles for the discovery of next-generation dual-atom ORR catalysts are provided.

I/O Lower-Bound Theory and Reinforcement Learning for Efficient Neural Network Inference Optimization

An automated optimization framework with a hierarchical two-layer tuning mechanism that synergizes theoretical I/O constraints with graph-level adaptive fusion while accounting for search overhead, the framework systematically explores high-performance execution patterns.

Machine learning surrogates for stability assessment of dry-stacked concrete waste assemblies: Comparing ensemble and graph-based architectures

The integration of non-standard materials into construction workflows is a key step toward circularity in the built environment. However, the lack of rapid stability assessment methods for non-standard assemblies limits their adoption, particularly in early-stage design when the potential for reducing environmental imp...

NEXUS-GO: Network-Extended Unified Sequence Embeddings for Gene Ontology Function Annotation

Protein function annotation by propagating protein language model embeddings over protein-protein interaction networks, across the full range from parameter-free multi-hop diffusion to learned graph neural networks (GCN, GAT, GraphSAGE) and their fusion. This release is the archived snapshot of the code and derived res...

Planting and Shaping the Neural Tree: Growing a Musical Collaborator Through Objective-Free Neuroevolution in Open-Ended Exploration

We present a live performance for experimental electronic music in which a continuously evolving neural network joins two human performers to form an improvising trio. Rather than training a generative model on pre-existing works, we use neuroevolution strategies to grow a feed-forward neural graph in real time, with n...