mlsanityData to 7 Oct 2026

R-GCN: The R Could Stand for Random

arXiv 2203.02424 ↗First posted 4 Mar 2022cs.LG cs.AI stat.MLcited by 9

Not on the map. Why?

Abstract (arXiv)

The inception of the Relational Graph Convolutional Network (R-GCN) marked a milestone in the Semantic Web domain as a widely cited method that generalises end-to-end hierarchical representation learning to Knowledge Graphs (KGs). R-GCNs generate representations for nodes of interest by repeatedly aggregating parameterised, relation-specific transformations of their neighbours. However, in this paper, we argue that the the R-GCN's main contribution lies in this "message passing" paradigm, rather than the learned weights. To this end, we introduce the "Random Relational Graph Convolutional Network" (RR-GCN), which leaves all parameters untrained and thus constructs node embeddings by aggregating randomly transformed random representations from neighbours, i.e., with no learned parameters. We empirically show that RR-GCNs can compete with fully trained R-GCNs in both node classification and link prediction settings.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 23 of its 43 references that are in the map. First posted on arXiv 4 Mar 2022.

Builds on

23 of 43 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  7. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  8. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  9. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  10. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  11. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  12. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
11 more
  1. 2018CatBoost: gradient boosting with categorical features supportcited by 208
  2. 2018SimplE Embedding for Link Prediction in Knowledge Graphscited by 195
  3. 2020The Surprising Power of Graph Neural Networks with Random Node Initializationcited by 190
  4. 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 186
  5. 2020Random Features Strengthen Graph Neural Networkscited by 184
  6. 2019Quaternion Knowledge Graph Embeddingscited by 175
  7. 2019Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphscited by 125
  8. 2021NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphscited by 71
  9. 2020Knowledge Graph Embeddings and Explainable AIcited by 15
  10. 2021Relational Graph Convolutional Networks: A Closer Lookcited by 8
  11. 2021Learning through structure: towards deep neuromorphic knowledge graph embeddingscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 1; 2024: 1; 2025: 0; 2026: 3.

9 papers.

  1. 2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
  2. 2022Weisfeiler and Leman Go Relationalcited by 28
  3. 2022pyRDF2Vec: A Python Implementation and Extension of RDF2Veccited by 8
  4. 2026No Need to Train Your RDB Foundation Modelcited by 8
  5. 2023Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representationcited by 3
  6. 2022Graph Neural Modeling of Network Flowscited by 2
  7. 2024Graph Residual based Method for Molecular Property Predictioncited by 0
  8. 2026Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Modelscited by 0
  9. 2026Sequential Learner Modeling Using Multi-Relational Graph Convolutional Networkscited by 0