mlsanityData to 14 Oct 2026

Encoder Embedding for General Graph and Node Classification

arXiv 2405.15473 ↗First posted 24 May 2024stat.ML cs.LG cs.SIcited by 4

Not on the map. Why?

Abstract (arXiv)

Graph encoder embedding, a recent technique for graph data, offers speed and scalability in producing vertex-level representations from binary graphs. In this paper, we extend the applicability of this method to a general graph model, which includes weighted graphs, distance matrices, and kernel matrices. We prove that the encoder embedding satisfies the law of large numbers and the central limit theorem on a per-observation basis. Under certain condition, it achieves asymptotic normality on a per-class basis, enabling optimal classification through discriminant analysis. These theoretical findings are validated through a series of experiments involving weighted graphs, as well as text and image data transformed into general graph representations using appropriate distance metrics.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 16 of its 43 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

16 of 43 references.

References · 16

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  3. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  4. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  5. 2014Graph-based Anomaly Detection and Description: A Surveycited by 183
  6. 2017Statistical inference on random dot product graphs: a surveycited by 70
  7. 2018On a 'Two Truths' Phenomenon in Spectral Graph Clusteringcited by 24
  8. 2021One-Hot Graph Encoder Embeddingcited by 16
  9. 2023Graph Encoder Ensemble for Simultaneous Vertex Embedding and Community Detectioncited by 8
  10. 2013Generalized Canonical Correlation Analysis for Classificationcited by 7
  11. 2018The Exact Equivalence of Distance and Kernel Methods for Hypothesis Testingcited by 7
  12. 2023Synergistic Graph Fusion via Encoder Embeddingcited by 6
4 more
  1. 2014Manifold Matching using Shortest-Path Distance and Joint Neighborhood Selectioncited by 5
  2. 2023Discovering Communication Pattern Shifts in Large-Scale Labeled Networks using Encoder Embedding and Vertex Dynamicscited by 5
  3. 2024Refined Graph Encoder Embedding via Self-Training and Latent Community Recoverycited by 5
  4. 2019Community Correlations and Testing Independence Between Binary Graphscited by 4

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2025Principal Graph Encoder Embedding and Principal Community Detectioncited by 2
  2. 2024Fast and Scalable Multi-Kernel Encoder Classifiercited by 0
  3. 2025Linear Discriminant Analysis with Gradient Optimizationcited by 0
  4. 2025Graph Neural Networks Powered by Encoder Embedding for Improved Node Learningcited by 0