Hierarchical Multi-Relational Graph Representation Learning for Large-Scale Drug-Drug Interaction Prediction
The author introduces a novel approach, Hierarchical Multi-Relational Graph Representation Learning (HMGRL), to predict drug-drug interactions by capturing both explicit and implicit correlations between drugs. The approach leverages diverse data sources and spectral clustering to enhance prediction accuracy.
Graph Representation Learning for Fatty Liver Disease Prediction
The author explores the potential of graph representation learning within a semi-supervised framework to predict fatty liver disease, emphasizing human-centric explanations through explainable GNNs.
Hierarchical Multi-Relational Graph Representation Learning for Large-Scale Prediction of Drug-Drug Interactions
薬物間相互作用の大規模予測のための階層的多関係グラフ表現学習
Graph Partial Label Learning with Potential Cause Discovering: A Novel Approach for GNNs
Proposing a novel method, GPCD, to enhance graph representation learning by extracting potential causes and mitigating label noise.
Shift Aggregate Extract Networks: Deep Hierarchical Decompositions for Graph Learning
Introducing an architecture based on deep hierarchical decompositions to learn effective representations of large graphs.
Neural Architecture Retrieval: Efficient Graph Representation Learning for Neural Architectures
Efficiently retrieve similar neural architectures using graph representation learning.
Simplified PCNet with Robustness: Enhancing Graph Neural Networks for Real-World Data
Enhancing the robustness and efficiency of Simplified PCNet for graph representation learning.
VQGraph: Rethinking Graph Representation Space for GNN-to-MLP Distillation
提案されたVQGRAPHフレームワークは、GNNからMLPへの知識蒸留において新しい最先端のパフォーマンスを達成します。
Can Large Language Models be Soft Prompted for Graph Learning Tasks?
Large Language Models can effectively comprehend graph information through soft prompts, as demonstrated by the GraphPrompter framework.
Spatial-Temporal Graph Representation Learning for Tactical Networks Future State Prediction
STGED framework outperforms baselines in predicting future network connectivity for tactical communication networks.
