node2vec
Top Cited Papers
- 13 August 2016
- conference paper
- research article
- Published by Association for Computing Machinery (ACM)
- Vol. 2016, 855-864
- https://doi.org/10.1145/2939672.2939754
Abstract
Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning approaches are not expressive enough to capture the diversity of connectivity patterns observed in networks. Here we propose node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks. In node2vec, we learn a mapping of nodes to a low-dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes. We define a flexible notion of a node's network neighborhood and design a biased random walk procedure, which efficiently explores diverse neighborhoods. Our algorithm generalizes prior work which is based on rigid notions of network neighborhoods, and we argue that the added flexibility in exploring neighborhoods is the key to learning richer representations. We demonstrate the efficacy of node2vec over existing state-of-the-art techniques on multi-label classification and link prediction in several real-world networks from diverse domains. Taken together, our work represents a new way for efficiently learning state-of-the-art task-independent representations in complex networks.Keywords
This publication has 22 references indexed in Scilit:
- Overlapping Communities Explain Core–Periphery Organization of NetworksProceedings of the IEEE, 2014
- A Deep Learning Approach to Link Prediction in Dynamic NetworksPublished by Society for Industrial & Applied Mathematics (SIAM) ,2014
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- A large-scale evaluation of computational protein function predictionNature Methods, 2013
- Molecular signatures database (MSigDB) 3.0Bioinformatics, 2011
- Leveraging social media networks for classificationData Mining and Knowledge Discovery, 2011
- Friends and neighbors on the WebSocial Networks, 2003
- Global protein function prediction from protein-protein interaction networksNature Biotechnology, 2003
- Nonlinear Dimensionality Reduction by Locally Linear EmbeddingScience, 2000
- A Global Geometric Framework for Nonlinear Dimensionality ReductionScience, 2000