graph neural networks

Acceleration response reconstruction of a television tower via deep learning with multi-scale feature fusion

Accurate reconstruction of structural response signals in structural health monitoring (SHM) remains challenging under complex operating conditions involving communication interruptions, sensor malfunctions, and environmental variability. To overcome these challenges, this study proposes a multi-scale temporal feature...

Mitigating Class Imbalance in Graph-Structured Data via Hierarchical Learning: Insights from Protein Binding Site Prediction

Learning from imbalanced data remains a major challenge for graph neural networks (GNNs), as minority nodes are not only rare but also structurally marginalized within the graph. We address this issue with CLARA, a hierarchical learning framework that decomposes node classification into two stages: a coarse subgraph-le...

Code-Agnostic Graph Neural Network Decoding from Detection Error Models: A Reconciled Quantitative and Structural Assessment

Graph neural network (GNN) decoders for quantum error correction have historically been locked to specific code families. The POLYMECHANON preprint [1,2] proposes a decoder whose sole input is the detection error model (DEM) — a tripartite graph of detectors, error mechanisms, and logical observables — making the code...

Code-Agnostic Graph Neural Network Decoding from Detection Error Models: A Reconciled Quantitative and Structural Assessment

Graph neural network (GNN) decoders for quantum error correction have historically been locked to specific code families. The POLYMECHANON preprint [1,2] proposes a decoder whose sole input is the detection error model (DEM) — a tripartite graph of detectors, error mechanisms, and logical observables — making the code...

Consistent Vulnerability Detection Using Graph Neural Networks

Leveraging Symbolic Artificial Intelligence and Fuzzy Logic for Materials Science: A Review of Methods, Challenges, and Applications to Scarce and Imperfect Experimental Data

This article explores the transformative potential of symbolic artificial intelligence (AI) in the field of materials science, particularly in leveraging experimental data. While state‐of‐the‐art methods like neural networks and statistical models face challenges with limited and imperfect data, symbolic AI offers a pr...

Simultaneous T1 and T2 Mapping in the Brain With QuantoRAGE: An MP2RAGE Variant Using T2-Prepared Inversion.

PURPOSE To develop and validate a repeatable and reproducible approach, QuantoRAGE, for simultaneous whole-brain T1 and T2 mapping using adiabatic magnetization preparation. METHODS QuantoRAGE is a 3D FLASH-based sequence using an adiabatic T2-prepared inversion followed by two readout blocks. Sequence repetitions wi...

STGCM: Sign-aware triple graph collaborative model for recommendation

Recommendation systems, as a core technology for mitigating information overload, play a crucial role across many fields. In recent years, graph neural networks (GNNs) have significantly improved recommendation performance by modeling user-item interactions as a graph structure. However, most existing sign-aware method...

When External Numerical Guards Detect Injected Faults in Neural-Network Inference

External guards can withhold an accelerator's output and trigger recovery, but their usefulness depends on which faults their numerical tests detect. We examine software fault-injection campaigns in convolutional networks, a vision transformer, and a decoder language model, distinguishing reported results from independ...

When External Numerical Guards Detect Injected Faults in Neural-Network Inference

External guards can withhold an accelerator's output and trigger recovery, but their usefulness depends on which faults their numerical tests detect. We examine software fault-injection campaigns in convolutional networks, a vision transformer, and a decoder language model, distinguishing reported results from independ...

Deep Ensemble Learning with Graph Attention Mechanisms for Molecular Classification of HIV Inhibitors

NeuroSymbolic-RLNet: a neuro-symbolic reinforcement learning framework for transparent sequential decision-making

The integration of symbolic reasoning with deep reinforcement learning presents a promising paradigm for achieving transparent and interpretable sequential decision-making in complex environments. This work introduces NeuroSymbolic-RLNet, a novel hybrid framework that combines symbolic state transition graphs with neur...