mlsanityData to 14 Oct 2026

From Primes to Paths: Enabling Fast Multi-Relational Graph Analysis

arXiv 2411.11149 ↗First posted 17 Nov 2024cs.LG cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-relational networks capture intricate relationships in data and have diverse applications across fields such as biomedical, financial, and social sciences. As networks derived from increasingly large datasets become more common, identifying efficient methods for representing and analyzing them becomes crucial. This work extends the Prime Adjacency Matrices (PAMs) framework, which employs prime numbers to represent distinct relations within a network uniquely. This enables a compact representation of a complete multi-relational graph using a single adjacency matrix, which, in turn, facilitates quick computation of multi-hop adjacency matrices. In this work, we enhance the framework by introducing a lossless algorithm for calculating the multi-hop matrices and propose the Bag of Paths (BoP) representation, a versatile feature extraction methodology for various graph analytics tasks, at the node, edge, and graph level. We demonstrate the efficiency of the framework across various tasks and datasets, showing that simple BoP-based models perform comparably to or better than commonly used neural models while offering improved speed and interpretability.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 55 references that are in the map. First posted on arXiv 17 Nov 2024.

Builds on

27 of 55 references.

References · 27

  1. 2017Graph Attention Networkscited by 8,923
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  4. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  5. 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
  6. 2020A Generalization of Transformer Networks to Graphscited by 661
  7. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  8. 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 266
  9. 2019DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphscited by 175
  10. 2017Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learningcited by 161
  11. 2020RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphscited by 118
  12. 2020A Survey on The Expressive Power of Graph Neural Networkscited by 111
15 more
  1. 2020CoDEx: A Comprehensive Knowledge Graph Completion Benchmarkcited by 102
  2. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  3. 2021Knowledge Graph Reasoning with Relational Digraphcited by 92
  4. 2013Multilayer Networkscited by 87
  5. 2020Relational Message Passing for Knowledge Graph Completioncited by 61
  6. 2014The structure and dynamics of multilayer networkscited by 51
  7. 2022A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphscited by 49
  8. 2016Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networkscited by 37
  9. 2020Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Studycited by 37
  10. 2015Compositional Vector Space Models for Knowledge Base Completioncited by 33
  11. 2016TensorLog: A Differentiable Deductive Databasecited by 29
  12. 2021Explainable Biomedical Recommendations via Reinforcement Learning Reasoning on Knowledge Graphscited by 7
  13. 2022R5: Rule Discovery with Reinforced and Recurrent Relational Reasoningcited by 7
  14. 2016Multilayer motif analysis of brain networkscited by 5
  15. 2023Analysing Biomedical Knowledge Graphs using Prime Adjacency Matricescited by 1

Built on by

Not cited yet.