Multi-scale attributed node embedding
From MaRDI portal
Abstract: We present network embedding algorithms that capture information about a node from the local distribution over node attributes around it, as observed over random walks following an approach similar to Skip-gram. Observations from neighborhoods of different sizes are either pooled (AE) or encoded distinctly in a multi-scale approach (MUSAE). Capturing attribute-neighborhood relationships over multiple scales is useful for a diverse range of applications, including latent feature identification across disconnected networks with similar attributes. We prove theoretically that matrices of node-feature pointwise mutual information are implicitly factorized by the embeddings. Experiments show that our algorithms are robust, computationally efficient and outperform comparable models on social networks and web graphs.
Recommendations
Cited in
(35)- Interpretable multi-scale graph descriptors via structural compression
- Multi-source information fusion based heterogeneous network embedding
- Structure-guided attributed network embedding with ``centroid enhancement
- MGAT: multi-view graph attention networks
- Synwalk: community detection via random walk modelling
- A general greedy approximation algorithm for finding minimum positive influence dominating sets in social networks
- Attributed network embedding via subspace discovery
- \textsc{gat2vec}: representation learning for attributed graphs
- Properties of vector embeddings in social networks
- Relation constrained attributed network embedding
- An effective heuristic clustering algorithm for mining multiple critical nodes in complex networks
- Core-periphery structure in networks: a statistical exposition
- An independent cascade walking based node embedding approach
- A Unifying Generative Model for Graph Learning Algorithms: Label Propagation, Graph Convolutions, and Combinations
- Stratified Stochastic Variational Inference for High-Dimensional Network Factor Model
- On embedding sequence correlations in attributed network for semi-supervised node classification
- Solving graph equipartition SDPs on an algebraic variety
- Multiway Spectral Graph Partitioning: Cut Functions, Cheeger Inequalities, and a Simple Algorithm
- AN EVOLUTIONARY MODEL OF SOCIAL NETWORK STRUCTURE DRIVEN BY INFORMATION INTERACTION
- Branching processes reveal influential nodes in social networks
- A divide-and-conquer algorithm for core-periphery identification in large networks
- Graph neural reaction diffusion models
- Efficient estimation in tensor Curie-Weiss and Erdős-Rényi Ising models
- Classification supported by community-aware node features
- Applications of dual regularized Laplacian matrix for community detection
- GPNet: simplifying graph neural networks via multi-channel geometric polynomials
- TRAIL: trajectory-based representation and integration for limiting over-smoothing
- Efficient quantification on large-scale networks
- Framelet message passing
- Graph sub-sampling for divide-and-conquer algorithms in large networks
- Dynamical analysis of an I2EH2S2R information spreading model with opinion divergence
- Beyond linear: a theoretical and empirical analysis of nonlinear GNNs for community detection
- Topology only pre-training: towards generalised multi-domain graph models
- Leveraging edge-aware graph neural networks to predict node load in backbone networks
- Scaling Fourier-Based Sparse Matrix Analysis on GPUs
This page was built for publication: Multi-scale attributed node embedding
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4958821)
