mlsanityData to 7 Oct 2026

A shallow neural model for relation prediction

arXiv 2101.09090 ↗First posted 22 Jan 2021cs.LG cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Knowledge graph completion refers to predicting missing triples. Most approaches achieve this goal by predicting entities, given an entity and a relation. We predict missing triples via the relation prediction. To this end, we frame the relation prediction problem as a multi-label classification problem and propose a shallow neural model (SHALLOM) that accurately infers missing relations from entities. SHALLOM is analogous to C-BOW as both approaches predict a central token (p) given surrounding tokens ((s,o)). Our experiments indicate that SHALLOM outperforms state-of-the-art approaches on the FB15K-237 and WN18RR with margins of up to 3% and 8% (absolute), respectively, while requiring a maximum training time of 8 minutes on these datasets. We ensure the reproducibility of our results by providing an open-source implementation including training and evaluation scripts at urlhttps://github.com/dice-group/Shallom.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 33 references that are in the map. First posted on arXiv 22 Jan 2021.

Builds on

19 of 33 references.

References · 19

  1. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  2. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
  3. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  4. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  5. 2016Complex Embeddings for Simple Link Predictioncited by 897
  6. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  7. 2014Distributed Representations of Sentences and Documentscited by 677
  8. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  9. 2020Knowledge Graphscited by 619
  10. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 264
  11. 2017Deep Complex Networkscited by 215
  12. 2020The Hardware Lotterycited by 160
7 more
  1. 2016Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Reviewcited by 155
  2. 2017Knowledge Graph Completion via Complex Tensor Factorizationcited by 80
  3. 2015Type-Constrained Representation Learning in Knowledge Graphscited by 34
  4. 2016ProjE: Embedding Projection for Knowledge Graph Completioncited by 26
  5. 2020Convolutional Complex Knowledge Graph Embeddingscited by 21
  6. 2016SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptionscited by 18
  7. 2018Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regionscited by 17

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 1; 2023: 0; 2024: 2.

6 papers.

  1. 2021Convolutional Hypercomplex Embeddings for Link Predictioncited by 15
  2. 2021Out-of-Vocabulary Entities in Link Predictioncited by 3
  3. 2021DRILL-- Deep Reinforcement Learning for Refinement Operators in ALCcited by 3
  4. 2022Hardware-agnostic Computation for Large-scale Knowledge Graph Embeddingscited by 3
  5. 2024Knowledge Graph Completion using Structural and Textual Embeddingscited by 1
  6. 2024Relations Prediction for Knowledge Graph Completion using Large Language Modelscited by 1