Walklets: Multiscale Graph Embeddings for Interpretable Network Classification
By Bryan Perozzi, Vivek Kulkarni, Steven S. Skiena. 2016
89 citations recorded by the source corpus.
We present Walklets, a novel approach for learning multiscale representations of vertices in a network. These representations clearly encode multiscale vertex relationships in a continuous vector space suitable for multi-label classification problems. Unlike previous work, the latent features generated using Walklets are analytically derivable, and human interpretable. Walklets uses the offsets between vertices observed in a random walk to learn a series of latent representations, each which captures successively larger relationships. This variety of dependency information allows the same representation strategy to model phenomenon which occur at different scales. We demonstrate Walklets' latent representations on several multi-label network classification tasks for social networks such as BlogCatalog, Flickr, and YouTube. Our results show that Walklets outperforms new methods based on neural matrix factorization, and can scale to graphs with millions of vertices and edges.
Subfields: Artificial Intelligence, Statistical and Nonlinear Physics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- William L. Hamilton
- Shirui Pan
- Jure Leskovec
- Rex Ying
- Guodong Long
- Chengqi Zhang
- Jing Jiang
- Marinka Zitnik
In Statistical and Nonlinear Physics
- Shirui Pan
- William L. Hamilton
- Chengqi Zhang
- Guodong Long
- Rex Ying
- Jure Leskovec
- Ruiqi Hu
- Jing Jiang
Citations in the corpus
- Representation Learning on Graphs: Methods and Applications (2017, methodology): “[47] extend the DeepWalk algorithm to learn embeddings using random walks that “skip” or “hop” over multiple nodes at each step, resulting in a proximity measure similar to GraRep [9], while Chamberlan et al.”
- Learning Graph Embedding With Adversarial Training Methods (2019, background): “Other random walk variants include hierarchical representation learning approach (HARP) [29], and discriminative deep random walk (DDRW) [30], and Walklets [31].”
- Graph Representation Learning (2020, methodology): “element-wise maximum or minimum, as in Qi et al. [2017], and it is also common to combine models based on Equation (5.”
- All You Need Is Low (Rank): Defending Against Adversarial Attacks on Graphs (2020, methodology): “In contrast to state-of-the-art approaches [16, 17, 30, 31, 37], t-PINE yields highly predictable representations on different multilabel classification problems.”
- Local Modeling of Attributed Graphs: Algorithms and Applications (2016, unknown): “Walklets: Multiscale Graph Embeddings for Interpretable Network Classification [119] We present Multiscale Network Embeddings (WALKLETS), a novel approach for learning multiscale”
- Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, background): “Perozzi et al. [184] extends DeepWalk by allowing random walks to skip over multiple nodes at each transition.”
- Representation Learning for Dynamic Graphs: A Survey (2019, background): “Perozzi et al. (2016) extends DeepWalk by allowing random walks to skip over multiple nodes at each transition.”