Label Propagation on K-partite Graphs with Heterophily
@article{Deng2017LabelPO, title={Label Propagation on K-partite Graphs with Heterophily}, author={Dingxiong Deng and Fan Bai and Yiqi Tang and Shuigeng Zhou and C. Shahabi and L. Zhu}, journal={ArXiv}, year={2017}, volume={abs/1701.06075} }
In this paper, for the first time, we study label propagation in heterogeneous graphs under heterophily assumption. Homophily label propagation (i.e., two connected nodes share similar labels) in homogeneous graph (with same types of vertices and relations) has been extensively studied before. Unfortunately, real-life networks are heterogeneous, they contain different types of vertices (e.g., users, images, texts) and relations (e.g., friendships, co-tagging) and allow for each node to… CONTINUE READING
Figures, Tables, and Topics from this paper
2 Citations
Are you on the right track? Learning career tracks for job movement analysis
- Computer Science
- 2018
- 2
- PDF
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
- Computer Science, Mathematics
- NeurIPS
- 2020
- 8
- PDF
References
SHOWING 1-10 OF 49 REFERENCES
Linearized and Single-Pass Belief Propagation
- Computer Science
- Proc. VLDB Endow.
- 2015
- 45
- Highly Influential
- PDF
Learning latent representations of nodes for classifying in heterogeneous social networks
- Computer Science
- WSDM
- 2014
- 79
- PDF
New Regularized Algorithms for Transductive Learning
- Mathematics, Computer Science
- ECML/PKDD
- 2009
- 218
- PDF
A Survey of Heterogeneous Information Network Analysis
- Computer Science, Physics
- IEEE Transactions on Knowledge and Data Engineering
- 2017
- 403
- PDF