Skip to content
Log in
Sponsored AI AM CLAUDE, A Beginner's Guide: Learn the basics of working with AI AI AM CLAUDE, A Beginner's Guide: Learn the basics of working with AI

Category

graph neural networks

1,904 papers

#graph neural networks Open access Sep 2026

Graph Neural Networks for Structural Genomics – Predicting Protein-Protein Interaction Networks from Sequence

Predicting protein-protein interactions (PPIs) is a critical task within structural genomics, aiming to understand cellular function and pathways. Traditional methods often rely on experimental techniques, which are costly and time-consuming. This research investigates the application of Graph Neural Networks (GNNs) to...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

Graph Neural Networks for Structural Genomics – Predicting Protein-Protein Interaction Networks from Sequence

Predicting protein-protein interactions (PPIs) is a critical task within structural genomics, aiming to understand cellular function and pathways. Traditional methods often rely on experimental techniques, which are costly and time-consuming. This research investigates the application of Graph Neural Networks (GNNs) to...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

Relational Neural Networks for Structured Data with Temporal Dependencies

This paper investigates the application of Relational Neural Networks (RNNs) to structured data exhibiting temporal dependencies. Traditional RNNs struggle to effectively represent complex relationships inherent in data where nodes are connected not just by proximity but also by defined interactions. We propose a novel...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

Multimodal Data Implicit Semantic Association Mining

This paper investigates the extraction of implicit semantic associations from multimodal data. The core claim is that humans inherently connect concepts across different modalities (e.g., images, text, audio) in subtle ways. We propose a novel framework leveraging deep learning to learn modality-specific representation...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

Multi-Scale Graph Neural Networks with Hierarchical Feature Aggregation

Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains, including node classification, link prediction, and graph classification. However, existing GNN models often struggle to effectively capture the intricate relationships within graphs, particularly those with varying degrees of granula...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

基于自适应的图神经网络参数调整算法

This paper presents a novel algorithm for automatically adjusting the parameters of graph neural networks (GNNs) using a self-adaptive approach. Traditional GNN parameter adjustment methods often rely on manual tuning, lacking the adaptability needed for complex datasets. This work introduces a new algorithm that lever...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

Adaptive Neural Network Weight Adjustment for Dynamic Node Adjustment

This paper investigates a novel dynamic approach to adaptive neural network weight adjustment, specifically focusing on the utilization of graph neural networks (GNNs) for dynamic node weighting. We introduce a method that intelligently adjusts node weights during training based on the network's internal state and data...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

Cognitive Graph Transformers for Multi-Modal Reasoning

This paper introduces a novel approach to multi-modal reasoning by integrating cognitive principles into the Graph Transformer architecture. We propose a 'cognitive memory' module that enhances the model's ability to capture and leverage past interactions and contextual information. The attention mechanism is then bias...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

Cognitive Graph Transformers for Multi-Modal Reasoning

This paper introduces a novel approach to multi-modal reasoning by integrating cognitive principles into the Graph Transformer architecture. We propose a 'cognitive memory' module that enhances the model's ability to capture and leverage past interactions and contextual information. The attention mechanism is then bias...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

##基于自适应的图神经网络模型

The ability to effectively model complex relationships within data is crucial for many applications in fields ranging from natural language processing to image recognition. Traditional graph neural networks (GNNs) offer a powerful framework for this, but their performance can be significantly impacted by the data's inh...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

Adaptive Kernel Methods for Non-Euclidean Data

Traditional kernel methods have demonstrated remarkable success in various machine learning tasks, particularly in capturing non-linear relationships within data. However, their applicability is severely limited when dealing with non-Euclidean data, where the notion of distance and similarity becomes ambiguous. This wo...

Jincheng Zhang · 0 citations
#graph neural networks Open access Sep 2026

Title: Emergent Topological Order in Graph Neural Networks

Graph neural networks (GNNs) have demonstrated remarkable success in various tasks involving graph data, including social network analysis, drug discovery, and knowledge graph reasoning. However, a fundamental challenge remains: effectively capturing and utilizing the inherent topological order within these graphs. Thi...

Jincheng Zhang · 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.