node2vec: Scalable Feature Learning for Networks
By Aditya Grover, Jure Leskovec. 2016
12,391 citations recorded by the source corpus.
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.
Subfields: Molecular Biology, Representation & Self-Supervised Learning, Graph Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Molecular Biology
- Jure Leskovec
- William L. Hamilton
- Stephan Günnemann
- Rex Ying
- Aleksandar Bojchevski
- Marinka Zitnik
- Jiaxuan You
- Petar Velickovic
In Representation & Self-Supervised Learning
- William L. Hamilton
- Jure Leskovec
- Stephan Günnemann
- Yoshua Bengio
- Aleksandar Bojchevski
- Dacheng Tao
- Jian Tang
- Philip S. Yu
In Graph Learning
- William L. Hamilton
- Jure Leskovec
- Stephan Günnemann
- Aleksandar Bojchevski
- Rex Ying
- Marinka Zitnik
- Matthias Fey
- Jian Tang
Citations in the corpus
- Semi-Supervised Classification with Graph Convolutional Networks (2016, background): “LINE (Tang et al., 2015) and node2vec (Grover & Leskovec, 2016) extend DeepWalk with more sophisticated random walk or breadth-first search schemes.”
- Inductive Representation Learning on Large Graphs (2017, positive): “The majority of these approaches directly optimize the embeddings for each node using matrix-factorization-based objectives, and do not naturally generalize to unseen data, since they make predictions on nodes in a single, fixed graph [5, 11, 23, 28, 35, 36, 37, 39].”
- Predicting multicellular function through multi-layer tissue networks (2017, methodology): “…size, d , Network neighborhood strategy, S , Regularization strength, λ 1: for i ∈ T do 2: for u ∈ V i do 3: N i ( u ) = Node2vecWalk ( G i ,u,S ) (Grover and Leskovec, 2016) 4: end for 5: end for 6: while f 1 ,f 2 ,... ,f | M | not converged do 7: for i ∈ M do 8: if i ∈ T then 9: for u ∈ V…”
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, methodology): “Finally, in the network analysis community, several works constructed graph embeddings [28, 38, 12, 17, 44] methods inspired by the Word2Vec technique [27].”
- Stochastic Training of Graph Convolutional Networks (2017, background): “…Welling, 2016; Berg et al., 2017) and knowledge graphs (Schlichtkrull et al., 2017), outperforming multi-layer perceptron (MLP) models that do not use the graph structure and graph embedding approaches (Perozzi et al., 2014; Tang et al., 2015; Grover & Leskovec, 2016) that do not use node features.”
- Variational Graph Auto-Encoders (2016, methodology): “For DW, we use the implementation provided by the authors of [8] with standard settings used in their paper, i.”
- Strategies for Pre-training Graph Neural Networks (2019, methodology): “In the first category are methods that use local random walk-based objectives (Grover & Leskovec, 2016; Perozzi et al., 2014; Tang et al., 2015) and methods that reconstruct a graph’s adjacency matrix, e.g. , by predicting edge existence (Hamilton et al., 2017a; Kipf & Welling, 2016).”
- Joint Topic-Semantic-aware Social Recommendation for Online Voting (2017, methodology): “Word2vec as well as associated Skip-Gram model are extensively used in document classification [15], dependency parser [4], and network embedding [8].”
- Compositional Fairness Constraints for Graph Embeddings (2019, methodology): “…and matrix factorization techniques (Ng et al., 2001), with recent years witnessing a surge in methods that rely on random-walk based objectives (Grover & Leskovec, 2016; Perozzi et al., 2014), deep au-toencoders (Wang et al., 2016), and graph neural networks (Hamilton et al., 2017a; Kipf &…”
- Auto-GNN: Neural architecture search of graph neural networks (2019, methodology): “Graph neural networks (GNN) [1, 2] has been demonstrated that it could achieve superior performance in modeling graph-structured data, within various domains such as social media [3–6] and bioinformatics [7, 8].”
- Relational inductive biases, deep learning, and graph networks (2018, background): “…work has also focused on building generative models of graphs (Li et al., 2018; De Cao and Kipf, 2018; You et al., 2018; Bojchevski et al., 2018), and unsupervised learning of graph embeddings (Perozzi et al., 2014; Tang et al., 2015; Grover and Leskovec, 2016; Garc´ıa-Dur´an and Niepert, 2017).”
- Position-aware Graph Neural Networks (2019, background): “…of nodes in graphs (Hamilton et al., 2017b) has led to advances on tasks such as node classification (Kipf & Welling, 2017), link prediction (Grover & Leskovec, 2016), graph classification (Ying et al., 2018b) and graph generation (You et al., 2018b), with successful applications across…”
- Unsupervised Inductive Whole-Graph Embedding by Preserving Graph Proximity (2019, methodology): “Example methods include DEEPWALK, NODE2VEC (Grover & Leskovec, 2016), GRAPHSAGE, etc. Notice that the former two use direct encoding as its node embedding model as described previously, while GRAPHSAGE uses neighbor aggregation.”
- Deep Graph Infomax (2018, methodology): “Most prominently, the random-walk objective is known to over-emphasize proximity information at the expense of structural information (Ribeiro et al., 2017), and performance is highly dependent on hyperparameter choice (Grover & Leskovec, 2016; Perozzi et al., 2014).”
- Representation Learning on Graphs with Jumping Knowledge Networks (2018, neutral): “2017; Grover & Leskovec, 2016; Tang et al., 2015).”
- Representation Learning on Graphs: Methods and Applications (2017, methodology): “The colorings for both figures were generated using different settings of the node2vec node embedding method [27], described in Section 2.”