← Back to all news
arXiv Machine Learning By Dongxiao He, Ruqiong Zhang, Zhizhi Yu, Ling Ding, Di Jin, Guangquan Xu, Zhiyong Feng

Query Entity-Oriented Graph Neural Networks for Knowledge Graph Completion

Read the original on arXiv Machine Learning →

The paper introduces Q-GNN, a graph neural network that explicitly conditions on the query entity for knowledge graph completion. Unlike prior methods that use only the query relation to guide message passing, Q-GNN incorporates the query entity’s local structural context and semantic type to modulate messages and guide attention. Experiments in both transductive and inductive settings show that this approach improves performance over existing GNN-based methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 3

PEARL: Path-Entity Aligned Relational Learning with Contextual Subgraphs for Inductive Knowledge Graph Completion

PEARL is a new framework for inductive knowledge graph completion that treats relational paths as context-conditioned reasoning signals. It builds a query‑specific contextual subgraph from the query entities’ neighborhoods and uses a large language model‑guided retriever to select semantically relevant paths. By constructing a bipartite interaction graph over paths, contextual entities, and a global subgraph representation, and applying a dual‑view contrastive objective, PEARL adapts path embeddings to local and global structural evidence, achieving the best average Hits@10 on WN18RR, FB15k‑237, and NELL‑995.

By Yunchi Yang, Longlong Li, Cunquan Qu
llmsragbenchmarks
More like this →
arXiv Machine Learning
Aug 28

SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning

The paper introduces SLM-Conditioned Hierarchical Relation Routing, a graph neural network architecture that incorporates a small language model to guide message selection in labeled property graphs. It combines structural states, node and relationship property encodings, and relationship types into messages, then uses a parameter‑efficient language model to generate target‑conditioned routing queries that filter relevant messages and route information across relation‑level summaries. The resulting representation updates a topology anchor with bounded residuals, preserving structural evidence while allowing contextual semantic information to influence predictions, and offers interpretable analysis at both neighbor and relationship‑type levels.

By Michal Podstawski
llms
More like this →