IEEE Transactions on Knowledge and Data Engineering · 2022 · 82 citations · 51 references
ComputingComputer ScienceFeature EngineeringKnowledge TransferMachine LearningDeep LearningGraph-based LearningRepresentation LearningSemi-supervised LearningTransfer LearningAdversarial Domain AdaptationConvolutionDomain AdaptationGraph Convolutional NetworksGraph Neural NetworksGraph Representation LearningGraph Transfer LearningNode Classification
This paper studies the problem of cross-network node classification to overcome the insufficiency of labeled data in a single network. It aims to leverage the label information in a partially labeled source network to assist node classification in a completely unlabeled or partially labeled target network. Existing methods for single network learning cannot solve this problem due to the domain shift across networks. Some multi-network learning methods heavily rely on the existence of cross-network connections, thus are inapplicable for this problem. To tackle this problem, we propose a novel graph transfer learning framework AdaGCN by leveraging the techniques of adversarial domain adaptation and graph convolution. It consists of two components: a semi-supervised learning component and an adversarial domain adaptation component. The former aims to learn class discriminative node representations with given label information of the source and target networks, while the latter contributes to mitigating the distribution divergence between the source and target domains to facilitate knowledge transfer. Extensive empirical evaluations on real-world datasets show that AdaGCN can successfully transfer class information with a low label rate on the source network and a substantial divergence between the source and target domains.
51
Laurens van der Maaten, Geoffrey E. Hinton · Journal of Machine Learning Research · 2008 · 35.7K citations
Sinno Jialin Pan, Qiang Yang · IEEE Transactions on Knowledge and Data Engineering · 2009 · 23.2K citations
Aditya Grover, Jure Leskovec · 2016 · 10.9K citations
Guillem Cucurull, Arantxa Casanova, Adriana Romero et al. · arXiv (Cornell University) · 2017 · 8.3K citations · Full text