Skip to content

Category

graph neural networks

1,890 papers

#graph neural networks Open access Sep 2026

Structural Representation in Crystal Property Prediction: A Controlled Benchmark on Band Gaps

This Zenodo record contains the complete reproducibility package for the study Structural Representation in Crystal Property Prediction: A Controlled Benchmark on Band Gaps. The benchmark evaluates how structural representation, model capacity, and training-data availability affect crystal band-gap prediction under a c...

Matthew Osvaldo, Matthew Jun Hao Kang, ETHAN YICONG Pang et al. · 0 citations
#graph neural networks Open access Sep 2026

THERMODYNAMIC COMPRESSION OF LOGIC: A Theoretical Spatiotemporal Graph Neural Network (ST-GNN) Framework for High-Fidelity Intuition

ABSTRACT Classical cognitive psychology has historically explored intuition as a heuristic, an evolutionary mental shortcut often susceptible to cognitive biases (System 1). This paper proposes an alternative framework grounded in the HEPOE Theory (High Entropy Predictive Organization Efficiency), suggesting that intui...

Camila Leão de Matos Brezolin, Sidnei Brezolin de Freitas · 0 citations
#graph neural networks Dataset Open access Sep 2026

DefectGNN-training graphs

This dataset contains the processed graph inputs and corresponding target labels used to train, validate, and independently evaluate the primary DefectGNN model. The data represent equiatomic atomic configurations encoded as graph for graph neural network regression.Each dataset includes a CSV file listing the serializ...

Yuqing Huang · 0 citations
#graph neural networks Open access Sep 2026

THERMODYNAMIC COMPRESSION OF LOGIC: A Theoretical Spatiotemporal Graph Neural Network (ST-GNN) Framework for High-Fidelity Intuition

ABSTRACT Classical cognitive psychology has historically explored intuition as a heuristic, an evolutionary mental shortcut often susceptible to cognitive biases (System 1). This paper proposes an alternative framework grounded in the HEPOE Theory (High Entropy Predictive Organization Efficiency), suggesting that intui...

Camila Leão de Matos Brezolin, Sidnei Brezolin de Freitas · 0 citations
#graph neural networks Open access Sep 2026

Computational Primes: A Systematic Framework for Partitioning Neural Network Computation Across Analog and Digital Domains

Twelve irreducible operations (P1-P12) with known physical implementations, and four without, as a basis for deciding which parts of a neural network belong in the analog domain. 114 algorithms are factored into these primes; the paper builds a compiler that decomposes a compute graph, assigns each prime to a domain, f...

Michael Bieg · 0 citations
#graph neural networks Open access Sep 2026

Morphological Memory: Grounding Synthetic Agent Architectures in Basal Cognition and Non-Neural Morphogenesis

Overview Contemporary Large Language Model (LLM) agent architectures treat memory primarily as retrieval over an append-only retrospective log. This paradigm incurs four foundational operational pathologies: Retrospective bias: Memory prioritises what was logged over what is dynamically needed. Write-time salience fixa...

Amity, Andrew Craucamp · 0 citations
#graph neural networks Open access Sep 2026

Morphological Memory: Grounding Synthetic Agent Architectures in Basal Cognition and Non-Neural Morphogenesis

Overview Contemporary Large Language Model (LLM) agent architectures treat memory primarily as retrieval over an append-only retrospective log. This paradigm incurs four foundational operational pathologies: Retrospective bias: Memory prioritises what was logged over what is dynamically needed. Write-time salience fixa...

Amity, Andrew Craucamp · 0 citations
#graph neural networks Open access Sep 2026

Artificial Intelligence-Driven Design and Optimization of Advanced Drug Delivery Systems: From Formulation Prediction to Clinical Translation: A Comprehensive Review

Advanced drug delivery systems (DDS) — including polymeric and lipid nanoparticles, lipid nanoparticles (LNPs) for nucleic acid therapeutics, solid oral dosage forms, and three-dimensional (3D)-printed and stimuli-responsive platforms — require the simultaneous optimization of dozens of interacting formulation and proc...

Avinash Bajpai, Sachin Sharma · 0 citations
#graph neural networks Dataset Open access Sep 2026

DefectGNN-training graphs

This dataset contains the processed graph inputs and corresponding target labels used to train, validate, and independently evaluate the primary DefectGNN model. The data represent equiatomic atomic configurations encoded as graph for graph neural network regression.Each dataset includes a CSV file listing the serializ...

Yuqing Huang · 0 citations
#graph neural networks Review Open access Sep 2026

Pre-operative neural substrates of deep brain stimulation outcomes: A systematic review and cross-disorder network synthesis

Background Deep brain stimulation (DBS) is an established therapy for movement and psychiatric disorders, yet its effects vary substantially across individuals. The pre-operative brain provides the individual circuitry upon which DBS acts, but how this circuitry shapes surgical outcomes remains poorly characterized. Me...

Y. Bai, Tiffany A. Rodrigues, Andrew Z. Yang et al. · 0 citations
#graph neural networks Dataset Open access Sep 2026

Dataset: Integrating Structural and Semantic Analysis for Code Smell Refactoring Prediction

The project bridges traditional static code analysis (Object-Oriented metrics) with advanced embedding representation learning to predict refactoring interventions on code-smelly methods. The predictive framework models a supervised binary classification task across 10 distinct target refactoring operations. Data Sourc...

Andrea Lanza, Matteo Bochicchio, Francesca Arcelli Fontana · 0 citations
#graph neural networks Dataset Open access Sep 2026

Research data for "Online Decentralized Estimation of Network Connectivity in Cooperative Robotic Systems Using Graph Neural Networks"

This repository contains the datasets, analysis scripts, and experiment configuration used to generate the results presented in our research paper "Online Decentralized Estimation of Network Connectivity in Cooperative Robotic Systems Using Graph Neural Networks". This is a condensed release containing only the materia...

Anonymous · 0 citations

From tech blogs

See all →
Microsoft Research Blog Jul 13, 2026

Verifying Rust cryptography in SymCrypt, from standards to code

Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves. The post Verifying Rust cryptography in SymCrypt, from standards to code appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.