node2vec: Scalable Feature Learning for Networks

@article{Grover2016node2vecSF,
  title={node2vec: Scalable Feature Learning for Networks},
  author={Aditya Grover and Jure Leskovec},
  journal={Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  year={2016}
}
  • Aditya Grover, J. Leskovec
  • Published 3 July 2016
  • Computer Science, Mathematics, Medicine
  • Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. [...] Key Method 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…Expand
Network Embedding: An Overview
TLDR
This paper reviews significant contributions to network embedding in the last decade and looks at four methods: Spectral Clustering, DeepWalk, Large-scale Information Network Embedding (LINE), and node2vec. Expand
Inductive Graph Embeddings through Locality Encodings
TLDR
This work proposes to use a set of basic predefined local encodings as the basis of a learning algorithm that generalizes well across unseen or distant regions in the network, both in unsupervised settings, when combined with language model learning, as well as in supervised tasks. Expand
Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
TLDR
Graph2Gauss is proposed - an approach that can efficiently learn versatile node embeddings on large scale (attributed) graphs that show strong performance on tasks such as link prediction and node classification and the benefits of modeling uncertainty are demonstrated. Expand
Distributed Representations of Subgraphs
TLDR
This work formulates a novel subgraph embedding problem based on an intuitive property of subgraphs and proposes SubVec, an unsupervised scalable algorithm to learn feature representations of arbitrary sub graphs and demonstrates usability of features learned by SubVEC by leveraging them for community detection problem, where it significantly out performs non-trivial baselines. Expand
Efficient Estimation of Node Representations in Large Graphs using Linear Contexts
TLDR
This paper proposes a simple alternate method which is as effective as previous methods, but being much faster at learning node representations, and employs a restricted number of permutations over the immediate neighborhood of a node as context to generate its representation. Expand
Distributed Representation of Subgraphs
TLDR
Sub2vec offers an approach to generate a richer vocabulary of features of subgraphs to support representation and reasoning and is highlighted by highlighting the usability of sub2vec by leveraging it for network mining tasks, like community detection. Expand
Attributed Network Embedding for Learning in a Dynamic Environment
TLDR
DANE first provides an offline method for a consensus embedding and then leverages matrix perturbation theory to maintain the freshness of the end embedding results in an online manner, and performs extensive experiments to corroborate the effectiveness and efficiency of the proposed framework. Expand
TNE: A Latent Model for Representation Learning on Networks
TLDR
This paper introduces a general framework to enhance the embeddings of nodes acquired by means of the random walk-based approaches, and assigns each vertex to a topic with the favor of various statistical models and community detection methods, and then generates the enhanced community representations. Expand
Core2Vec: A Core-Preserving Feature Learning Framework for Networks
TLDR
This paper proposes core2vec, a new algorithmic framework for learning low dimensional continuous feature mapping for a node and utilizes the well-established idea that nodes with similar core numbers play equivalent roles in the network and hence induce a novel and an organic notion of neighbourhood. Expand
Sub2Vec: Feature Learning for Subgraphs
TLDR
This work forms subgraph embedding problem based on two intuitive properties of subgraphs and proposes Sub2Vec, an unsupervised algorithm to learn feature representations of arbitrary sub graphs, and shows that Sub2 Vec gets significant gains over state-of-the-art methods. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 50 REFERENCES
LRBM: A Restricted Boltzmann Machine Based Approach for Representation Learning on Linked Data
TLDR
The proposed LRBM model, a restricted Boltzmann machine model developed for representation learning on linked data, aims to extract the latent feature representation of each node from both node attributes and network structures, non-linearly map each pair of nodes to the links, and use hidden units to control the mapping. Expand
Supervised random walks: predicting and recommending links in social networks
TLDR
An algorithm based on Supervised Random Walks is developed that naturally combines the information from the network structure with node and edge level attributes and outperforms state-of-the-art unsupervised approaches as well as approaches that are based on feature extraction. Expand
A Deep Learning Approach to Link Prediction in Dynamic Networks
TLDR
A novel deep learning framework, i.e., Conditional Temporal Restricted Boltzmann Machine (ctRBM), which predicts links based on individual transition variance as well as influence introduced by local neighbors is proposed, which outperforms existing algorithms in link inference on dynamic networks. Expand
LINE: Large-scale Information Network Embedding
TLDR
A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures. Expand
Leveraging Label-Independent Features for Classification in Sparsely Labeled Networks: An Empirical Study
TLDR
This work explores a complimentary approach to within-network classification, based on the use of label-independent (LI) features - i.e., features calculated without using the values of class labels - and shows that, in many cases, it is a combination of a few diverse network-based structural characteristics that is most informative. Expand
DeepWalk: online learning of social representations
TLDR
DeepWalk is an online learning algorithm which builds useful incremental results, and is trivially parallelizable, which make it suitable for a broad class of real world applications such as network classification, and anomaly detection. Expand
It's who you know: graph mining using recursive structural features
TLDR
ReFeX (Recursive Feature eXtraction), a novel algorithm, that recursively combines local features with neighborhood features; and outputs regional features -- capturing "behavioral" information in large graphs, is proposed. Expand
GraRep: Learning Graph Representations with Global Structural Information
TLDR
A novel model for learning vertex representations of weighted graphs that integrates global structural information of the graph into the learning process and significantly outperforms other state-of-the-art methods in such tasks. Expand
Gated Graph Sequence Neural Networks
TLDR
This work studies feature learning techniques for graph-structured inputs and achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be matched to abstract data structures. Expand
RolX: structural role extraction & mining in large graphs
TLDR
This paper proposes RolX (Role eXtraction), a scalable (linear in the number of edges), unsupervised learning approach for automatically extracting structural roles from general network data, and compares network role discovery with network community discovery. Expand
...
1
2
3
4
5
...