Skip to Main content Skip to Navigation
New interface
Conference papers

BiasedWalk: Biased Sampling for Representation Learning on Graphs

Abstract : Network embedding algorithms are able to learn latent feature representations of nodes, transforming networks into lower dimensional vector representations. Typical key applications, which have effectively been addressed using network embeddings, include link prediction, multilabel classification and community detection. In this paper, we propose Biased-Walk, a scalable, unsupervised feature learning algorithm that is based on biased random walks to sample context information about each node in the network. Our random-walk based sampling can behave as Breath-First-Search (BFS) and Depth-First-Search (DFS) samplings with the goal to capture homophily and role equivalence between the nodes in the network. We have performed a detailed experimental evaluation comparing the performance of the proposed algorithm against various baseline methods, on several datasets and learning tasks. The experiment results show that the proposed method outperforms the baseline ones in most of the tasks and datasets.
Complete list of metadata

Cited literature [28 references]  Display  Hide  Download
Contributor : Fragkiskos Malliaros Connect in order to contact the contributor
Submitted on : Tuesday, December 18, 2018 - 12:40:01 PM
Last modification on : Tuesday, November 29, 2022 - 11:56:14 AM
Long-term archiving on: : Wednesday, March 20, 2019 - 9:23:23 AM


Files produced by the author(s)



Duong Nguyen, Fragkiskos Malliaros. BiasedWalk: Biased Sampling for Representation Learning on Graphs. International Workshop on High Performance Big Graph Data Management, Analysis, and Mining (BigGraphs), Dec 2018, Seattle, WA, United States. ⟨10.1109/bigdata.2018.8621872⟩. ⟨hal-01958902⟩



Record views


Files downloads