BiasedWalk: Biased Sampling for Representation Learning on Graphs
This addresses network embedding for tasks like link prediction and classification, but it is incremental as it builds on existing random-walk methods.
The paper tackles the problem of learning node representations for graphs by proposing BiasedWalk, an unsupervised algorithm using biased random walks to capture homophily and role equivalence, and it outperforms baseline methods in most tasks and datasets.
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 BiasedWalk, 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.