Summary of Da-moe: Addressing Depth-sensitivity in Graph-level Analysis Through Mixture Of Experts, by Zelin Yao et al.
DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Expertsby Zelin Yao, Chuang Liu, Xianke…
DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Expertsby Zelin Yao, Chuang Liu, Xianke…
GraphXAIN: Narratives to Explain Graph Neural Networksby Mateusz Cedro, David MartensFirst submitted to arxiv on:…
Enhancing Graph Neural Networks in Large-scale Traffic Incident Analysis with Concurrency Hypothesisby Xiwen Chen, Sayed…
High-Pass Graph Convolutional Network for Enhanced Anomaly Detection: A Novel Approachby Shelei Li, Yong Chai…
GITSR: Graph Interaction Transformer-based Scene Representation for Multi Vehicle Collaborative Decision-makingby Xingyu Hu, Lijun Zhang,…
Quantum Rationale-Aware Graph Contrastive Learning for Jet Discriminationby Md Abrar Jahin, Md. Akmol Masud, M.…
A General Recipe for Contractive Graph Neural Networks – Technical Reportby Maya Bechler-Speicher, Moshe EliasofFirst…
Using Half-Precision for GNN Trainingby Arnab Kanti Tarafder, Yidong Gong, Pradeep KumarFirst submitted to arxiv…
The Graph’s Apprentice: Teaching an LLM Low Level Knowledge for Circuit Quality Estimationby Reza Moravej,…
MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddingsby Ashkan Golgoon, Ryan Franks,…