This paper proposes a real-time actionable approach for modeling surgical team dynamics using time-expanded interaction graphs. The model enables efficient inference with a static graph neural network, predicting procedural efficiency and supporting counterfactual analysis to identify changes in communication structure.
We propose PathBoost, a gradient tree boosting method for graph-level classification and regression, which learns discriminative path-based features directly from the input graph structure. This method introduces adaptations for binary classification, incorporates multiple node and edge attributes, and automatically selects anchor nodes, outperforming or matching graph neural networks and graph kernel approaches on several benchmark datasets.
This paper introduces Mask-Morph Graph U-Net (MMGUNet), a practical approach addressing the limitation of hierarchical Graph U-Net architectures in crash simulations. It aims to improve generalisability by retaining fixed coarse graph connectivity while improving spatial correspondence, offering a faster alternative to computationally expensive finite element methods.
This paper introduces Logic-GNN, a neuro-symbolic framework that leverages Temporal Graph Neural Networks and Graph Kolmogorov Complexity to detect data entry errors in clinical records. It identifies anomalies as "grammatical violations" in a latent logical grammar of medical interactions, achieving an F1-score of 0.94 on a large clinical dataset.
This research proposes a framework to interpret protein language model representations by projecting them onto protein contact graphs and applying SoftBlobGIN, a Graph Isomorphism Network. This method performs structure-aware message passing to learn functional substructures, achieving 92.8% accuracy in enzyme classification and providing auditable structural explanations.
This research reveals a mini-batch dependent heuristic in popular GNN-based link prediction models, enabled by batch-normalization layers. This bias can lead to an overestimation of the models' ability to learn generalized graph representations, rather than transferring underlying graph properties.
This paper surveys GNN-based communication in multi-agent reinforcement learning (MARL), noting a lack of explicit structure in existing approaches. It proposes a generalized GNN-based communication process to make the underlying concepts more obvious and accessible.
Este trabalho propõe um novo modelo para treinar Redes Neurais Gráficas (GNNs) sensíveis à justiça, aprimorando o framework CAF. A abordagem utiliza uma estratégia de treinamento em duas fases, editando o grafo para ajustar a homofilia e integrando perdas contrastivas e ambientais modificadas para melhorar a predição e a justiça.
This research proposes semantically enriching investor micro-blogs to enhance opinion-aware emotion analysis. It augments the StockEmotions dataset with granular opinion graphs using an LLM pipeline and demonstrates improved classification performance with Graph Neural Networks.
O título sugere 'OntoKG', um método para construção de grafos de conhecimento orientado a ontologias com roteamento intrínseco-relacional. Contudo, a ausência de conteúdo impede qualquer análise aprofundada do material.