Methods › Graphs › Graph Embeddings › DeepWalk

DeepWalk

67 papers tagged archive 2025-07-28

Introduced by Bryan Perozzi et al. in DeepWalk: Online Learning of Social Representations

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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.

The goal is to learn a latent representation, not only a probability distribution of node co-occurrences, and so as to introduce a mapping function Φv ∈V ↦ℝ^(|V|×d). This mapping Φ represents the latent social representation associated with each vertex v in the graph. In practice, Φ is represented by a |V| ×d matrix of free parameters.

PaperSource

Papers archive 2025-07-28

30 shown of 67, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 57 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Representation Learning24
Network Embedding19
Node Classification17
Link Prediction16
Graph Embedding12
Graph Representation Learning8
Community Detection5
Recommendation Systems5
BIG-bench Machine Learning4
Clustering4
General Classification4
Graph Neural Network4
Attribute3
Contrastive Learning3
Anomaly Detection2
Classification2
Dimensionality Reduction2
Feature Engineering2
Graph Learning2
Graph Sampling2

Usage over time archive 2025-07-28

Papers per year tagged with DeepWalk: 2014 to 2025, peak 13 13 0 2014: 1 paper 2014 2015: 3 papers 2015 2016: 0 papers 2016 2017: 4 papers 2017 2018: 5 papers 2018 2019: 11 papers 2019 2020: 9 papers 2020 2021: 13 papers 2021 2022: 8 papers 2022 2023: 3 papers 2023 2024: 7 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (67 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Graph Embeddings

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections