graph neural networks

Learning mesh-free discrete differential operators with self-supervised graph neural networks

Mesh-free numerical methods provide flexible discretisations for complex geometries; however, classical meshless discrete differential operators typically trade low computational cost for limited accuracy or high accuracy for substantial per-stencil computation. We introduce a parametrised framework for learning mesh-f...

M2FNet: a multiscale graph-convolution collaborative network with node interaction attention for hyperspectral change detection

Hyperspectral image change detection faces challenges from spectral redundancy and spatial-scale diversity, which hinder the extraction of discriminative features and lead to pseudo-change noise. To address these issues, we propose M2FNet: a multiscale graph-convolution collaborative network with node interaction atten...

CD-BAN: Cyclodextrin Bilinear Attention Network for Inclusion Complex Affinity Classification

Source code for CD-BAN, a dual-branch graph neural network with a bilinear cross-attention layer that classifies drug-cyclodextrin inclusion-complex binding affinity (Strong: K > 10,000 M⁻¹ vs. Weak: K < 100 M⁻¹) from 2D SMILES alone, without 3D geometry or handcrafted descriptors. Trained only on the binary extremes,...

Graph-based Seismic Earthquake Prediction Neural Network

Confidential preliminary research document.Intellectual property of Drescher Károly.

manofseven7/HetST-GNN: HetST-GNN v1.0.0

Official code for the paper: HetST-GNN: Relation-Aware Graph Neural Networks with Temporal Conditioning for Back-Order Prediction in Multi-Echelon Supply Chains This release contains the source code used in the paper.

The Fractal Graph Rewriting Framework: A Scale-Dependent Approach to LLM Optimization

FGRF v3.0: Validated structural probe for LLM weight matrices, with spectral estimators and a reproducible trained-vs-untrained signature across Qwen2.5-0.5B, SmolLM2-360M, and GPT-2-medium. FGRF v2.0: Version 2 represents an evolution from the original proof-of-concept. It reframes FGRF from a direct optimizer into a...

Graph attribute encoding and sparse graph integral histograms for efficient aerial localization

Visual localization for unmanned aerial vehicles in satellite-denied environments traditionally relies on matching onboard camera imagery to geospatial reference maps. However, direct image-based matching is highly susceptible to seasonal, environmental, and temporal variations. To overcome these limitations, we propos...

Regression-based dynamic graph convolutional network for intelligent monitoring of coastal wetlands

Multispectral images (MSIs) with representative spectral bands and superior spatial resolution are usually considered for fine classification of wetlands; however, traditional MSI feature extraction and classification models may be suboptimal to identify differences between similar ground objects. To come up with a sol...

Graph-based Seismic Earthquake Prediction Neural Network

Confidential preliminary research document.Intellectual property of Drescher Károly.

Business Analysis for Strategic Commerce: Data-driven Decision Making in Competitive Markets

In today's competitive market environment, business analysis has developed into a necessity beyond just describing reports to becoming a strategy for data-driven decision making. This research paper offers an integrated approach to applying business analysis to managerial decision analytics for creating a sustainable c...

SpaMet-GNN: a donor-aware graph neural network framework for identifying reproducible spatial expression programs in gastrointestinal cancers

Business Analysis for Strategic Commerce: Data-driven Decision Making in Competitive Markets

In today's competitive market environment, business analysis has developed into a necessity beyond just describing reports to becoming a strategy for data-driven decision making. This research paper offers an integrated approach to applying business analysis to managerial decision analytics for creating a sustainable c...