Inclement
发表于 2025-3-28 14:39:20
http://reply.papertrans.cn/17/1677/167617/167617_41.png
疏忽
发表于 2025-3-28 22:05:28
Edged Weisfeiler-Lehman Algorithmn the representation of a node is updated by aggregating representations from itself and neighbor nodes recursively. Similar to the propagation-aggregation methodology, the Weisfeiler-Lehman (1-WL) algorithm tests isomorphism through color refinement according to color representations of a node and
ADORE
发表于 2025-3-28 23:07:13
http://reply.papertrans.cn/17/1677/167617/167617_43.png
颠簸地移动
发表于 2025-3-29 03:16:50
Graph-Guided Multi-view Text Classification: Advanced Solutions for Fast Inference of parameters and high memory requirements, making it difficult to implement in some real-time scenarios or limited resources. Therefore, researchers attempt to use lightweight Graph Neural Networks(GNN) with excellent feature expression as an alternative solution. However, current GNN-based method
Cultivate
发表于 2025-3-29 08:37:59
Invariant Graph Contrastive Learning for Mitigating Neighborhood Bias in Graph Neural Network Based tite graphs. Despite the success of existing GNN-based recommender systems, they generally suffer from the . problem, which breaks the homophily assumption in various real-world recommendation scenarios. The neighborhood bias stems from the mixed complex local patterns caused by the diverse user pre
IRS
发表于 2025-3-29 11:32:08
Key Substructure-Driven Backdoor Attacks on Graph Neural Networksing backdoor attacks have two main limitations: Firstly, they lack flexibility and effectiveness in associating predefined substructures with predicted labels, limiting their ability to influence the classifier. Secondly, the injection locations of these substructures lack stealth, failing to exploi
友好关系
发表于 2025-3-29 19:35:17
http://reply.papertrans.cn/17/1677/167617/167617_47.png
concubine
发表于 2025-3-29 23:01:23
Multi-graph Fusion and Virtual Node Enhanced Graph Neural Networkses. However, many GNN-based techniques assume complete and accurate graph relations. Unfortunately, this assumption often diverges from reality, as real-world scenarios frequently exhibit missing and erroneous edges within graphs. Consequently, GNNs that rely solely on the original graph structure i
秘方药
发表于 2025-3-30 01:14:52
http://reply.papertrans.cn/17/1677/167617/167617_49.png
妈妈不开心
发表于 2025-3-30 06:33:02
http://reply.papertrans.cn/17/1677/167617/167617_50.png