Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Phuc, Luu Huu, Thapa, Ratan Bahadur, Nayyeri, Mojtaba, Wu, Jingcheng, Kharlamov, Evgeny, Staab, Steffen
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911694010187776
author Phuc, Luu Huu
Thapa, Ratan Bahadur
Nayyeri, Mojtaba
Wu, Jingcheng
Kharlamov, Evgeny
Staab, Steffen
author_facet Phuc, Luu Huu
Thapa, Ratan Bahadur
Nayyeri, Mojtaba
Wu, Jingcheng
Kharlamov, Evgeny
Staab, Steffen
contents We introduce Graph-Augmented Sequence-to-Sequence (GA-S2S), a novel framework that integrates a T5-small encoder-decoder with a Relational Graph Attention Network (RGAT) to improve link prediction in knowledge graphs. While existing Seq2Seq models rely solely on surface-level textual descriptions of entities and relations and at best, flatten the neighborhoods of a query entity into a single linear sequence, thereby discarding the inherent graph structure, GA-S2S jointly encodes both textual features and the full $k$-hop subgraph topology surrounding the query entity. By integrating raw encoder outputs with RGAT's relation-aware embeddings, our model captures and leverages richer multi-hop relational patterns and textual information. Our preliminary experiments on the CoDEx dataset demonstrate that GA-S2S outperforms competitive Seq2Seq-based baseline models, achieving up to a 19\% relative gain in link prediction accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18211
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction
Phuc, Luu Huu
Thapa, Ratan Bahadur
Nayyeri, Mojtaba
Wu, Jingcheng
Kharlamov, Evgeny
Staab, Steffen
Computation and Language
Artificial Intelligence
We introduce Graph-Augmented Sequence-to-Sequence (GA-S2S), a novel framework that integrates a T5-small encoder-decoder with a Relational Graph Attention Network (RGAT) to improve link prediction in knowledge graphs. While existing Seq2Seq models rely solely on surface-level textual descriptions of entities and relations and at best, flatten the neighborhoods of a query entity into a single linear sequence, thereby discarding the inherent graph structure, GA-S2S jointly encodes both textual features and the full $k$-hop subgraph topology surrounding the query entity. By integrating raw encoder outputs with RGAT's relation-aware embeddings, our model captures and leverages richer multi-hop relational patterns and textual information. Our preliminary experiments on the CoDEx dataset demonstrate that GA-S2S outperforms competitive Seq2Seq-based baseline models, achieving up to a 19\% relative gain in link prediction accuracy.
title Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.18211