mlsanityData to 14 Oct 2026

Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction

arXiv 2305.13059 ↗First posted 22 May 2023cs.LG cs.AI cs.SIcited by 9

Not on the map. Why?

Abstract (arXiv)

We propose KGT5-context, a simple sequence-to-sequence model for link prediction (LP) in knowledge graphs (KG). Our work expands on KGT5, a recent LP model that exploits textual features of the KG, has small model size, and is scalable. To reach good predictive performance, however, KGT5 relies on an ensemble with a knowledge graph embedding model, which itself is excessively large and costly to use. In this short paper, we show empirically that adding contextual information - i.e., information about the direct neighborhood of the query entity - alleviates the need for a separate KGE model to obtain good performance. The resulting KGT5-context model is simple, reduces model size significantly, and obtains state-of-the-art performance in our experimental study.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 18 of its 22 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

18 of 22 references.

References · 18

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  4. 2016Complex Embeddings for Simple Link Predictioncited by 902
  5. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  6. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  7. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 329
  8. 2018SimplE Embedding for Link Prediction in Knowledge Graphscited by 195
  9. 2019PyTorch-BigGraph: A Large-scale Graph Embedding Systemcited by 119
  10. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 91
  11. 2022Sequence-to-Sequence Knowledge Graph Completion and Question Answeringcited by 75
  12. 2019A Re-evaluation of Knowledge Graph Completion Methodscited by 73
6 more
  1. 2020DGL-KE: Training Knowledge Graph Embeddings at Scalecited by 67
  2. 2020HittER: Hierarchical Transformers for Knowledge Graph Embeddingscited by 54
  3. 2019GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embeddingcited by 40
  4. 2020MLMLM: Link Prediction with Mean Likelihood Masked Language Modelcited by 22
  5. 2022BESS: Balanced Entity Sampling and Sharing for Large-Scale Knowledge Graph Completioncited by 2
  6. 2022Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddingscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 3; 2026: 2.

9 papers.

  1. 2025LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Modelscited by 22
  2. 2024Deja vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoningcited by 1
  3. 2025Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Contextcited by 1
  4. 2023A Benchmark for Semi-Inductive Link Prediction in Knowledge Graphscited by 0
  5. 2023Better Together: Enhancing Generative Knowledge Graph Completion with Language Models and Neighborhood Informationcited by 0
  6. 2024In-Context Learning with Topological Information for Knowledge Graph Completioncited by 0
  7. 2025KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphscited by 0
  8. 2026Autoregressive Models for Knowledge Graph Generationcited by 0
  9. 2026Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Predictioncited by 0