Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction

Adrian Kochsiek, Apoorv Saxena, Inderjeet Nair, Rainer Gemulla
5/22/2023
cs.LGcs.AIcs.SI

No official code found. Best implementation: uma-pi1/kgt5-context (12 stars, last commit 2024-06-20).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

uma-pi1/kgt5-contextCommunity100%
123Python2 years ago

Similar Papers

Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs

88% match2025

Farspredict: A benchmark dataset for link prediction

87% match2023

KGEx: Explaining Knowledge Graph Embeddings via Subgraph Sampling and Knowledge Distillation

84% match2023

LinkLogic: A New Method and Benchmark for Explainable Knowledge Graph Predictions

84% match1 repo32024

Improving rule mining via embedding-based link prediction

83% match1 repo32024

Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models

83% match1 repo92023

Cite this paper

@article{kochsiek2023friendly,
  title  = {Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction},
  author = {Adrian Kochsiek and Apoorv Saxena and Inderjeet Nair and Rainer Gemulla},
  year   = {2023},
  eprint = {2305.13059},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.13059v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.13059.svg)](https://codeofpaper.com/paper/2305.13059)

Discussion