.png){kind=icon}
返回
Label-Aware Augmentation for Long-Tailed Cross-Network Node Classification
.png){kind=icon}
PRE
AI
DOI：10.1111/exsy.70212.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Cross-network node classification (CNC) aims to classify the nodes of an unlabeled graph by leveraging a graph with rich labelled nodes. The node representation and cross-network discrepancy are two important issues in CNC. Most methods argue that the node representation is crucial to the performance of CNC and learn the representation based on the rich neighbourhood. However, in applications, the networks follow a long-tailed distribution in their node degrees, that is, most nodes are tail nodes linked to a small amount of neighbours. The sparsity of neighbourhood challenges existing methods in representation and classification. To this end, we propose a label-aware cross-network node classification (LA-CNC) method. First, a label-consistent augmentation is designed for each network to enrich the representation by augmenting the neighbourhood of tail nodes. Second, a label contrast loss is introduced and combined with adversarial loss to enhance the distinguishability of cross-network invariant representation. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on several datasets.
Keyword:
contrast learning
cross-network node classification
long-tail
representation learning
期刊
IF:
2.3
论文数:
2.6K
被引数:
3.8K
机构
引用论文
DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification.png)
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
OAAI
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningIF0
OAAI分享收藏
ArnetMinerProceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining
Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data miningIF0
PREAI
分享收藏Structure enhanced prototypical alignment for unsupervised cross-domain node classificationNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏
查看更多内容