Graph Neural Network Inference Optimization Based on Adversarial Training and Contrastive Representation Distillation

Graph Neural Network (GNN) excels in node classification tasks, but its message-passing mechanism causes neighbor-fetching latency, limiting deployment in latency-sensitive applications. Despite being less accurate than GNN in node classification tasks, Multi-Layer Perceptron (MLP) is preferred in p...

Deskribapen osoa

Xehetasun bibliografikoak

Egile nagusia:	LI Qiang, TAN Xingyi, ZHENG Wei, LIU Zhen, YANG Wenhai
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	Editorial Office of Computer Engineering 2026-01-01
Saila:	Jisuanji gongcheng
Gaiak:	graph neural network (gnn)|knowledge distillation|inference acceleration|contrastive learning|adversarial training
Sarrera elektronikoa:	https://www.ecice06.com/fileup/1000-3428/PDF/20260110.pdf
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!