DeepWalk: online learning of social representations

@article{Perozzi2014DeepWalkOL,
  title={DeepWalk: online learning of social representations},
  author={Bryan Perozzi and Rami Al-Rfou and Steven Skiena},
  journal={Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining},
  year={2014}
}
  • Bryan PerozziRami Al-RfouS. Skiena
  • Published 26 March 2014
  • Computer Science
  • Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining
We present DeepWalk, a novel approach for learning latent representations of vertices in a network. [] Key MethodDeepWalk uses local information obtained from truncated random walks to learn latent representations by treating walks as the equivalent of sentences. We demonstrate DeepWalk's latent representations on several multi-label network classification tasks for social networks such as BlogCatalog, Flickr, and YouTube. Our results show that DeepWalk outperforms challenging baselines which are allowed a…
View on ACM
arxiv.org
7,152 Citations
Highly Influential Citations
1,622
Background Citations
2,442
Methods Citations
3,529
Results Citations
108

Figures and Tables from this paper

7,152 Citations

Don't Walk, Skip!: Online Learning of Multi-scale Network Embeddings

The results show that WALKLETS outperforms new methods based on neural matrix factorization, and outperform DeepWalk by up to 10% and LINE by 58% Micro-F1 on challenging multi-label classification tasks.

Max-Margin DeepWalk: Discriminative Learning of Network Representation

MMDW is a unified NRL framework that jointly optimizes the max-margin classifier and the aimed social representation learning model, and indicates that the model is more discriminative than unsupervised ones, and the experimental results demonstrate that the method achieves a significant improvement than other state-of-the-art methods.

Discriminative Deep Random Walk for Network Classification

This paper presents Discriminative Deep Random Walk (DDRW), a novel method for relational network classification that significantly outperforms DeepWalk on multilabel network classification tasks, while retaining the topological structure in the latent space.

subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs

It is demonstrated that subgraph vectors learnt by the approach could be used in conjunction with classifiers such as CNNs, SVMs and relational data clustering algorithms to achieve significantly superior accuracies on both supervised and unsupervised learning tasks.

Learning Edge Representations via Low-Rank Asymmetric Projections

This work proposes a new method for embedding graphs while preserving directed edge information, and explicitly model an edge as a function of node embeddings, and proposes a novel objective, the graph likelihood, which contrasts information from sampled random walks with non-existent edges.

Learning distributed representations for large-scale dynamic social networks

This work proposes Dnps, a novel nodes embedding approach for acquiring distributed representations of large-scale dynamic social networks, and develops a damping based positive sampling (DpS) algorithm to learn the hierarchical structure of social networks.

DeepInf: Social Influence Prediction with Deep Learning

Inspired by the recent success of deep neural networks in a wide range of computing applications, an end-to-end framework to learn users' latent feature representation for predicting social influence is designed, suggesting the effectiveness of representation learning for social applications.

Efficient Estimation of Node Representations in Large Graphs using Linear Contexts

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.

Topic-aware latent models for representation learning on networks

TNE: A Latent Model for Representation Learning on Networks

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.
...

References

SHOWING 1-10 OF 50 REFERENCES

Relational learning via latent social dimensions

This work proposes to extract latent social dimensions based on network information, and then utilize them as features for discriminative learning, and outperforms representative relational learning methods based on collective inference, especially when few labeled data are available.

Scalable learning of collective behavior based on sparse social dimensions

This work proposes an edge-centric clustering scheme to extract sparse social dimensions that can efficiently handle networks of millions of actors while demonstrating comparable prediction performance as other non-scalable methods.

Leveraging Label-Independent Features for Classification in Sparsely Labeled Networks: An Empirical Study

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.

It's who you know: graph mining using recursive structural features

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.

Leveraging relational autocorrelation with latent group models

A latent group model (LGM) is proposed for relational data, which discovers and exploits the hidden structures responsible for the observed autocorrelation among class labels and improves model performance, increases inference efficiency, and enhances the understanding of the datasets.

Multi-label relational neighbor classification using social context features

This paper proposes a multi-label iterative relational neighbor classifier that employs social context features (SCRN), which incorporates a class propagation probability distribution obtained from instances' social features, which are in turn extracted from the network topology.

Representation Learning: A Review and New Perspectives

Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks.

Semi-Supervised Classification of Network Data Using Very Few Labels

  • Frank LinWilliam W. Cohen
  • Computer Science
    2010 International Conference on Advances in Social Networks Analysis and Mining
  • 2010
Another simple and intuitive semi-supervised learning method based on random graph walk that outperforms wvRN by a large margin on several benchmark datasets when very few labels are available and dramatically reduces the amount of labeled data required to achieve the same classification accuracy.

A Neural Probabilistic Language Model

This work proposes to fight the curse of dimensionality by learning a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences.

Polyglot: Distributed Word Representations for Multilingual NLP

This work quantitatively demonstrates the utility of word embeddings by using them as the sole features for training a part of speech tagger for a subset of these languages and investigates the semantic features captured through the proximity of word groupings.