IEEE Transactions on Network Science and Engineering · 2022 · 19 citations · 42 references
ComputingComputer ScienceKnowledge RepresentationMachine LearningNatural Language ProcessingDeep LearningGraph AnalyticsGraph MiningGraph-based LearningNetwork InferenceComplex NetworksGraph ClassificationGraph Neighborhood AggregationGraph Neural NetworksGraph Representation LearningNeighborhood AggregationNode Classification
The emerging graph neural networks (GNNs) have demonstrated impressive performance on the node classification problem in complex networks. However, existing GNNs are mainly devised to classify nodes in a (partially) labeled graph. To classify nodes in a newly-collected unlabeled graph, it is desirable to transfer label information from an existing labeled graph. To address this cross-graph node classification problem, we propose a graph infomax method that is domain adaptive. Node representations are computed through neighborhood aggregation. Mutual information is maximized between node representations and global summaries, encouraging node representations to encode the global structural information. Conditional adversarial networks are employed to reduce the domain discrepancy by aligning the multimodal distributions of node representations. Experimental results in real-world datasets validate the performance of our method in comparison with the state-of-the-art baselines.
42
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
Conditional Generative Adversarial Nets
Mehdi Mirza, Simon Osindero · arXiv (Cornell University) · 2014 · 8.9K citations · Full text