{"url":"/method/deepwalk","slug":"deepwalk","name":"DeepWalk","full_name":"DeepWalk","full_name_withheld":false,"description_markdown":"**DeepWalk** learns embeddings (social representations) of a graph's vertices, by modeling a stream of short random walks. Social representations are latent features of the vertices that capture neighborhood similarity and community membership. These latent representations encode social relations in a continuous vector space with a relatively small number of dimensions. It generalizes neural language models to process a special language composed of a set of randomly-generated walks. \r\n\r\nThe goal is to learn a latent representation, not only a probability distribution of node co-occurrences, and so as to introduce a mapping function $\\Phi \\colon v \\in V \\mapsto \\mathbb{R}^{|V|\\times d}$.\r\nThis mapping $\\Phi$ represents the latent social representation associated with each vertex $v$ in the graph. In practice, $\\Phi$ is represented by a $|V| \\times d$ matrix of free parameters.","description_state":"present","introduced_year":null,"introduced_by":{"title":"DeepWalk: Online Learning of Social Representations","paper":"/paper/deepwalk-online-learning-of-social","first_author":"Bryan Perozzi","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deepwalk-online-learning-of-social"},"source":{"url":"http://arxiv.org/abs/1403.6652v2","title":"DeepWalk: Online Learning of Social Representations","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Graphs","area_id":"graphs","collection":"Graph Embeddings","url":"/methods/category/graph-embeddings","pwc_aliases":[]}],"n_papers_tagged":67,"archive_num_papers":67,"papers_newest_first":[{"paper":null,"title":"Node Embeddings via Neighbor Embeddings","date":"2025-03-31","arxiv_id":"2503.23822","n_code_links":0,"syntology":null},{"paper":null,"title":"A quantum annealing approach to graph node embedding","date":"2025-03-08","arxiv_id":"2503.06332","n_code_links":0,"syntology":null},{"paper":null,"title":"Heterogeneous Graph Pre-training Based Model for Secure and Efficient Prediction of Default Risk Propagation among Bond Issuers","date":"2025-01-04","arxiv_id":"2501.03268","n_code_links":0,"syntology":null},{"paper":"/paper/two-layer-walk-a-community-aware-graph","title":"Two Layer Walk: A Community-Aware Graph Embedding","date":"2024-12-17","arxiv_id":"2412.12933","n_code_links":1,"syntology":null},{"paper":null,"title":"Convergence Guarantees for the DeepWalk Embedding on Block Models","date":"2024-10-26","arxiv_id":"2410.20248","n_code_links":0,"syntology":null},{"paper":"/paper/network-analytics-for-anti-money-laundering-a","title":"Network Analytics for Anti-Money Laundering -- A Systematic Literature Review and Experimental Evaluation","date":"2024-05-29","arxiv_id":"2405.19383","n_code_links":1,"syntology":null},{"paper":"/paper/robustness-of-graph-embedding-methods-for","title":"Robustness of graph embedding methods for community detection","date":"2024-05-01","arxiv_id":"2405.00636","n_code_links":1,"syntology":null},{"paper":null,"title":"Hierarchical Information Enhancement Network for Cascade Prediction in Social Networks","date":"2024-03-22","arxiv_id":"2403.15257","n_code_links":0,"syntology":null},{"paper":null,"title":"Hyperdimensional Representation Learning for Node Classification and Link Prediction","date":"2024-02-26","arxiv_id":"2402.17073","n_code_links":0,"syntology":null},{"paper":null,"title":"Frustrated Random Walks: A Fast Method to Compute Node Distances on Hypergraphs","date":"2024-01-23","arxiv_id":"2401.13054","n_code_links":0,"syntology":null},{"paper":null,"title":"Reproducibility study of the Fairness-enhanced Node Representation Learning","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Drug Interaction Vectors Neural Network: DrIVeNN","date":"2023-08-26","arxiv_id":"2308.13891","n_code_links":0,"syntology":null},{"paper":null,"title":"Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness","date":"2023-04-24","arxiv_id":"2304.12036","n_code_links":0,"syntology":null},{"paper":null,"title":"Learning Heuristics for the Maximum Clique Enumeration Problem Using Low Dimensional Representations","date":"2022-10-30","arxiv_id":"2210.16963","n_code_links":0,"syntology":null},{"paper":"/paper/easyrec-an-easy-to-use-extendable-and","title":"EasyRec: An easy-to-use, extendable and efficient framework for building industrial recommendation systems","date":"2022-09-26","arxiv_id":"2209.12766","n_code_links":2,"syntology":null},{"paper":null,"title":"Large-Scale Privacy-Preserving Network Embedding against Private Link Inference Attacks","date":"2022-05-28","arxiv_id":"2205.14440","n_code_links":0,"syntology":null},{"paper":"/paper/a-practical-two-stage-ranking-framework-for","title":"A Practical Two-stage Ranking Framework for Cross-market Recommendation","date":"2022-04-27","arxiv_id":"2204.12682","n_code_links":1,"syntology":null},{"paper":null,"title":"GlobalWalk: Learning Global-aware Node Embeddings via Biased Sampling","date":"2022-01-22","arxiv_id":"2201.09882","n_code_links":0,"syntology":null},{"paper":"/paper/classic-graph-structural-features-outperform","title":"Classic Graph Structural Features Outperform Factorization-Based Graph Embedding Methods on Community Labeling","date":"2022-01-20","arxiv_id":"2201.08481","n_code_links":1,"syntology":null},{"paper":"/paper/contrastive-laplacian-eigenmaps-1","title":"Contrastive Laplacian Eigenmaps","date":"2022-01-14","arxiv_id":"2201.05493","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}},{"paper":"/paper/asymptotics-of-ell-2-regularized-network","title":"Asymptotics of $\\ell_2$ Regularized Network Embeddings","date":"2022-01-05","arxiv_id":"2201.01689","n_code_links":1,"syntology":null},{"paper":null,"title":"Learning Large-scale Network Embedding from Representative Subgraph","date":"2021-12-02","arxiv_id":"2112.01442","n_code_links":0,"syntology":null},{"paper":null,"title":"Generalizable Cross-Graph Embedding for GNN-based Congestion Prediction","date":"2021-11-10","arxiv_id":"2111.05941","n_code_links":0,"syntology":null},{"paper":null,"title":"Community detection using low-dimensional network embedding algorithms","date":"2021-11-04","arxiv_id":"2111.05267","n_code_links":0,"syntology":null},{"paper":"/paper/grape-fast-and-scalable-graph-processing-and","title":"GRAPE for Fast and Scalable Graph Processing and random walk-based Embedding","date":"2021-10-12","arxiv_id":"2110.06196","n_code_links":2,"syntology":null},{"paper":null,"title":"REFINE: Random RangE FInder for Network Embedding","date":"2021-08-24","arxiv_id":"2108.10703","n_code_links":0,"syntology":null},{"paper":null,"title":"NOTE: Solution for KDD-CUP 2021 WikiKG90M-LSC","date":"2021-07-05","arxiv_id":"2107.01892","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-modules-in-graph-contrastive","title":"Evaluating Modules in Graph Contrastive Learning","date":"2021-06-15","arxiv_id":"2106.08171","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}},{"paper":"/paper/crosswalk-fairness-enhanced-node","title":"CrossWalk: Fairness-enhanced Node Representation Learning","date":"2021-05-06","arxiv_id":"2105.02725","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":"/paper/evaluating-document-representations-for","title":"Evaluating Document Representations for Content-based Legal Literature Recommendations","date":"2021-04-28","arxiv_id":"2104.13841","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/representation-learning","name":"Representation Learning","papers":24},{"task":"/task/network-embedding","name":"Network Embedding","papers":19},{"task":"/task/node-classification","name":"Node Classification","papers":17},{"task":"/task/link-prediction","name":"Link Prediction","papers":16},{"task":"/task/graph-embedding","name":"Graph Embedding","papers":12},{"task":"/task/graph-representation-learning","name":"Graph Representation Learning","papers":8},{"task":"/task/community-detection","name":"Community Detection","papers":5},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":5},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":4},{"task":"/task/clustering","name":"Clustering","papers":4},{"task":"/task/classification","name":"General Classification","papers":4},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":4},{"task":"/task/attribute","name":"Attribute","papers":3},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":3},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":2},{"task":"/task/classification-1","name":"Classification","papers":2},{"task":"/task/dimensionality-reduction","name":"Dimensionality Reduction","papers":2},{"task":"/task/feature-engineering","name":"Feature Engineering","papers":2},{"task":"/task/graph-learning","name":"Graph Learning","papers":2},{"task":"/task/graph-sampling","name":"Graph Sampling","papers":2}],"tasks_shown":20,"n_tasks":57,"usage_by_year":[{"year":"2014","papers":1},{"year":"2015","papers":3},{"year":"2017","papers":4},{"year":"2018","papers":5},{"year":"2019","papers":11},{"year":"2020","papers":9},{"year":"2021","papers":13},{"year":"2022","papers":8},{"year":"2023","papers":3},{"year":"2024","papers":7},{"year":"2025","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/deepwalk"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}