graph neural networks

Graph Theory Applications In Artificial Intelligence And Data Science

Graph Theory has been established as a fundamental approach to modeling relational data in Artificial Intelligence and Data Science. In this paper, a thorough study of graph-related methods has been conducted with a special focus on Graph Neural Networks (GNNs) and its variants for processing non-Euclidean data structu...

Noise to One, Signal to Another: Under Strong Heterophily, a Separate Self-Path Decides Whether Edges Help a GNN

When edges are removed from a graph, do graph neural networks lose performance because they lose information, or because they lose specific structural signals? We study this with a controlled edge-removal probe. We sparsify graphs from 0% to 95% under three strategies: random removal, removal of cross-label (heterophil...

Dataset for: Selecting Descriptor Models and Graph Neural Networks For Structural Response Prediction Of Varying Geometric Complexity

This paper compares descriptor models and geometric point graph neural networks for structural response prediction in procedurally generated L-shaped brackets with zero to eight holes. Complexity is quantified using hole count, removed-area fraction, boundary multiplier, inverse compactness and normalized minimum ligam...

Artificial Intelligence of Things (AIoT): Technologies, Applications, and Challenges

Artificial Intelligence of Things (AIoT) refers to the deliberate pairing of artificial intelligence with the sensing and connectivity that the Internet of Things (IoT) already provides, so that the data streaming in from distributed devices turns into insight and, ultimately, action [1]. A properly designed AIoT syste...

Quantization fragility under image corruption is recipe-dependent: paired evidence from INT8 and FP8 object detectors: Reproducibility Package

Reproducibility package accompanying the manuscript Quantization fragility under image corruption is recipe-dependent: paired evidence from INT8 and FP8 object detectors, prepared for Neural Networks. The release contains analysis, pipeline, and validation code; frozen configurations and manifests; compact deterministi...

Dataset for: Selecting Descriptor Models and Graph Neural Networks For Structural Response Prediction Of Varying Geometric Complexity

This paper compares descriptor models and geometric point graph neural networks for structural response prediction in procedurally generated L-shaped brackets with zero to eight holes. Complexity is quantified using hole count, removed-area fraction, boundary multiplier, inverse compactness and normalized minimum ligam...

Code for: Selecting Descriptor Models and Graph Neural Networks For Structural Response Prediction Of Varying Geometric Complexity

This paper compares descriptor models and geometric point graph neural networks for structural response prediction in procedurally generated L-shaped brackets with zero to eight holes. Complexity is quantified using hole count, removed-area fraction, boundary multiplier, inverse compactness and normalized minimum ligam...

Compositional Quantum Heuristics for Max-Clique Detection

Abstract Quantum machine learning holds the promise of combining the success of classical machine learning methods with the power of quantum computing, however one of the largest obstacles facing the field is the problem of barren plateaus. Parameterised quantum circuits offer a flexible framework for developing quantu...

Cross-Document Neural Re-ranking via Query-Induced Subgraphs

AI-Powered Logic Gate Optimization for Efficient Electronic Design

Abstract The continuous development of modern electronic devices has resulted in increasingly complex Integrated Circuits (ICs). As the number of logic gates and circuit components increases, designing efficient electronic systems becomes more challenging. Engineers need to consider several important factors, including...

AI-Powered Logic Gate Optimization for Efficient Electronic Design

Abstract The continuous development of modern electronic devices has resulted in increasingly complex Integrated Circuits (ICs). As the number of logic gates and circuit components increases, designing efficient electronic systems becomes more challenging. Engineers need to consider several important factors, including...

Protein Language Model–Conditioned Graph Neural Networks for Multitask GPCR Ligand Activity Prediction

Predicting ligand activity across G protein-coupled receptors (GPCRs) requires models that capture both molecular structure and receptor-specific information while remaining robust to chemical and target-domain shifts. We developed a multimodal graph neural network that combines explicit ligand molecular graphs with fr...