KAUST DepartmentComputer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
KAUST Grant NumberFCC/1/1976-19-01
Preprint Posting Date2019-10-22
Online Publication Date2020-01-22
Print Publication Date2020-01-20
Permanent link to this recordhttp://hdl.handle.net/10754/660639
MetadataShow full item record
AbstractIn this paper, we study the graph-based semi-supervised learning for classifying nodes in attributed networks, where the nodes and edges possess content information. Recent approaches like graph convolution networks and attention mechanisms have been proposed to ensemble the first-order neighbors and incorporate the relevant neighbors. However, it is costly (especially in memory) to consider all neighbors without a prior differentiation. We propose to explore the neighborhood in a reinforcement learning setting and find a walk path well-tuned for classifying the unlabelled target nodes. We let an agent (of node classification task) walk over the graph and decide where to move to maximize classification accuracy. We define the graph walk as a partially observable Markov decision process (POMDP). The proposed method is flexible for working in both transductive and inductive setting. Extensive experiments on four datasets demonstrate that our proposed method outperforms several state-of-the-art methods. Several case studies also illustrate the meaningful movement trajectory made by the agent.
CitationAkujuobi, U., Zhang, Q., Yufei, H., & Zhang, X. (2020). Recurrent Attention Walk for Semi-supervised Classification. Proceedings of the 13th International Conference on Web Search and Data Mining. doi:10.1145/3336191.3371853
SponsorsThis work was partially supported and funded by King Abdullah University of Science and Technology (KAUST), under award number FCC/1/1976-19-01, and NSFC No. 61828302.
Conference/Event name13th ACM International Conference on Web Search and Data Mining, WSDM 2020