graph neural networks

An Efficient Graph Neural Network‐Based Routing Optimization Mechanism for Congestion‐Aware Software‐Defined Networks

ABSTRACT Software‐Defined Networking (SDN) has developed as a suitable solution for complex networks with a flexible and programmable networking paradigm. SDN infrastructure is facing critical challenges in efficient routing under dynamic and congestion‐prone conditions. This research paper proposes an efficient Improv...

Understanding Fairness–Privacy Interactions in Graph Neural Networks: A Literature Review, Taxonomy, and Open Challenges

Graph Neural Networks (GNNs) are increasingly applied to socially consequential tasks, such as disease surveillance on contact graphs, and credit scoring and fraud detection on financial transaction networks. In these settings, biased or unfair predictions can restrict access to opportunities and resources, while priva...

DSCrisk: A dual-view and substructure aware based method for drug-drug interaction risk-level prediction enhanced by contrastive learning.

A deep-learning framework that employs graph neural networks (GNNs) to encode a dual-view representation comprising molecular graphs and the DDI topology network and a partner-guided attention mechanism improves interpretability by revealing critical substructures associated with DDI risk.

Multi-centre validation of MELD-graph for automated focal cortical dysplasia detection using 7T compared to paired 3T MRI

Background: Software tools can support MRI diagnosis of focal cortical dysplasias (FCDs) - subtle, surgically-treatable lesions that underlie drug-resistant focal epilepsy (DRFE). MELD-graph, a widely used open-source tool combining surface-based morphometry with a convolutional neural network, was developed using 1.5T...

Formal Chemistry Definitions and Auditable Certificate Pipelines as Infrastructure for Trustworthy AI-Driven Materials Search

AI-driven materials discovery has advanced rapidly, with projects such as Google DeepMind's GNoME identifying over 380,000 candidate stable crystals through graph-network predictions. Yet a persistent trust gap remains: surrogate models can hallucinate stability, and opaque screening pipelines make it difficult for dow...

Towards a Virtual Embryo: A new approach methodology for probabilistic assessment of neural tube closure defects

Neural tube closure represents a critical morphogenetic event during early vertebrate embryogenesis. When genetic or chemical factors disrupt this process, embryos can develop severe birth defects such as spina bifida. To understand how these defects emerge, we built a computational agent-based model that functionalize...

SignReGraph: rethinking skeleton-based sign language recognition with masked self-supervision

Spatio-temporal graph foundation models for earth system intelligence: an end-to-end, continual, and multimodal learning framework

A structure-sequence synergistic learning framework for prioritizing functional peptides from food protein hydrolysates.

A structure-sequence synergistic learning framework for prioritizing functional peptide candidates from food protein hydrolysates that combines a pre-trained protein language model for contextual sequence encoding with a geometry-aware graph neural network for three-dimensional structural representation, and fuses both...

Dimensionless energy graph network with hard boundary embedding and finite element interpolation: Unsupervised variational solution framework for linear elastic and hyperelastic problems

Neural solvers for solid mechanics still face challenges related to loss-term balancing, representation on complex unstructured meshes, enforcement of essential boundary conditions, and scale sensitivity in energy-based optimization. This work proposes HiDEG-Net, a dimensionless energy graph network with hard boundary...

Learning attention-enhanced relation-sensitive knowledge graph embeddings with variable receptive fields for link prediction

Knowledge graph embedding aims to predict missing links by learning representations of entities and relations. However, existing methods often struggle to effectively capture interaction features at multiple scales and to suppress redundant information among these multi-scale features, which hinders the model’s ability...

Role of AI in Accurate and Disinformation‐Resilient Diagnosis of Ulcerative Colitis

Ulcerative colitis is a type of bowel disease that occurs in the innermost lining of the large intestine. If this persists, then the patient may have an increased risk of developing colon cancer. So disease detection in its earliest stage is very important for saving a patient from the risk of having cancer. In this pr...