mlsanityData to 7 Oct 2026

word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Data

arXiv 2003.12590 ↗First posted 27 Mar 2020cs.LG cs.DB cs.DMcited by 38

Not on the map. Why?

Abstract (arXiv)

Vector representations of graphs and relational structures, whether hand-crafted feature vectors or learned representations, enable us to apply standard data analysis and machine learning techniques to the structures. A wide range of methods for generating such embeddings have been studied in the machine learning and knowledge representation literature. However, vector embeddings have received relatively little attention from a theoretical point of view. Starting with a survey of embedding techniques that have been used in practice, in this paper we propose two theoretical approaches that we see as central for understanding the foundations of vector embeddings. We draw connections between the various approaches and suggest directions for future research.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 3; 2023: 9; 2024: 9; 2025: 6; 2026: 5.

38 papers.

Sort:

By area:

  1. 2021Combinatorial optimization and reasoning with graph neural networkscited by 267
  2. 2021Reconstruction for Powerful Graph Representationscited by 65
  3. 2021Graph Neural Networks with Local Graph Parameterscited by 51
  4. 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networkscited by 37
  5. 2023WL meet VCcited by 30
  6. 2023Fine-grained Expressivity of Graph Neural Networkscited by 25
  7. 2023Expectation-Complete Graph Representations with Homomorphismscited by 10
  8. 2024Tensor Graph Convolutional Network for Dynamic Graph Representation Learningcited by 8
  9. 2024FSW-GNN: A Bi-Lipschitz WL-Equivalent Graph Neural Networkcited by 8
  10. 2023Self-Discriminative Modeling for Anomalous Graph Detectioncited by 6
  11. 2024On the H"older Stability of Multiset and Graph Neural Networkscited by 6
  12. 2023Topological Node2vec: Enhanced Graph Embedding via Persistent Homologycited by 5
26 more
  1. 2024Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Visioncited by 5
  2. 2025Molecular Machine Learning in Chemical Process Designcited by 5
  3. 2024A Survey of Source Code Representations for Machine Learning-Based Cybersecurity Taskscited by 4
  4. 2024Multimodal Deep Learning for Low-Resource Settings: A Vector Embedding Alignment Approach for Healthcare Applicationscited by 4
  5. 2023Structural Node Embeddings with Homomorphism Countscited by 3
  6. 2025Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learningcited by 3
  7. 2021Accurately Modeling Biased Random Walks on Weighted Graphs Using textitNode2vec+cited by 2
  8. 2022On the Surprising Behaviour of node2veccited by 2
  9. 2023Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation Learningcited by 2
  10. 2026Grables: Tabular Learning Beyond Independent Rowscited by 2
  11. 2021Network representation learning systematic review: ancestors and current development statecited by 1
  12. 2023From structure mining to unsupervised exploration of atomic octahedral networkscited by 1
  13. 2025Node Embeddings via Neighbor Embeddingscited by 1
  14. 2025Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forwardcited by 1
  15. 2021Scaling up graph homomorphism for classification via samplingcited by 0
  16. 2022MultiSAGE: a multiplex embedding algorithm for inter-layer link predictioncited by 0
  17. 2023Estimation of embedding vectors in high dimensionscited by 0
  18. 2024Sequence graphs realizations and ambiguity in language modelscited by 0
  19. 2024MPXGAT: An Attention based Deep Learning Model for Multiplex Graphs Embeddingcited by 0
  20. 2024A Structural Feature-Based Approach for Comprehensive Graph Classificationcited by 0
  21. 2025Skeleton-Guided Learning for Shortest Path Searchcited by 0
  22. 2025Predicting effect of novel treatments using molecular pathways and real-world datacited by 0
  23. 2026FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distancescited by 0
  24. 2026PatTree: a novel approach for automated creation of multimodal, graph-based patient representations for medical classification taskscited by 0
  25. 2026AutoGrable: What Is a Good Graph for a Table?cited by 0
  26. 2026Graph neural networks for sampling-invariant embeddings of organized signal setscited by 0