CiteSeer: an automatic citation indexing system
Proceedings of the third ACM conference on Digital libraries
The anatomy of a large-scale hypertextual Web search engine
WWW7 Proceedings of the seventh international conference on World Wide Web 7
Finding related pages in the World Wide Web
WWW '99 Proceedings of the eighth international conference on World Wide Web
Learning from labeled and unlabeled data on a directed graph
ICML '05 Proceedings of the 22nd international conference on Machine learning
Spectral clustering of biological sequence data
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining
Graph nodes clustering with the sigmoid commute-time kernel: A comparative study
Data & Knowledge Engineering
Improving fuzzy multilevel graph embedding through feature selection technique
SSPR'12/SPR'12 Proceedings of the 2012 Joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Spectral embedding for dynamic social networks
Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining
Learning social network embeddings for predicting information diffusion
Proceedings of the 7th ACM international conference on Web search and data mining
Hi-index | 0.00 |
In this paper, we propose the Directed Graph Embedding (DGE) method that embeds vertices on a directed graph into a vector space by considering the link structure of graphs. The basic idea is to preserve the locality property of vertices on a directed graph in the embedded space. We use the transition probability together with the stationary distribution of Markov random walks to measure such locality property. It turns out that by exploring the directed links of the graph using random walks, we can get an optimal embedding on the vector space that preserves the local affinity which is inherent in the directed graph. Experiments on both synthetic data and real-world Web page data are considered. The application of our method to Web page classification problems gets a significant improvement comparing with state-of-art methods.