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.
arXiv:2606. 05639v1 Announce Type: new Abstract: Knowledge Graph Completion (KGC) aims at predicting missing triplets from incomplete knowledge graphs, which is crucial for downstream applications.
arXiv:2606. 16509v1 Announce Type: new Abstract: Link prediction in knowledge graphs fundamentally depends on the quality of learned embeddings for entities and relations.
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.
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.
arXiv:2407.12703v5 Announce Type: cross Abstract: Fine-tuning pre-trained language models (PLMs) has recently shown a potential to improve knowledge graph completion (KGC). However, most PLM-based me...
arXiv:2610.18198v1 Announce Type: new Abstract: Knowledge graph link prediction involving unseen entities and relations requires learning transferable reasoning patterns from observed graph structure...
Knowledge graphs (KGs) organize real-world knowledge as triplets and underpin many downstream applications. Due to their inherent incompleteness, knowledge graph completion (KGC) is widely studied and is typically formulated as triplet prediction, with link prediction as the dominant paradigm.
arXiv:2606. 29860v1 Announce Type: new Abstract: Knowledge graphs (KGs) organize real-world knowledge as triplets and underpin many downstream applications.
arXiv:2511.04473v3 Announce Type: replace Abstract: Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While various...
GLM-RAG introduces a graph language model (GLM) based retriever for retrieval‑augmented generation over knowledge graphs. The study compares GLM‑based, graph neural network (GNN)‑based, and vector‑search retrievers across single‑ and multi‑hop settings, emphasizing transferability to unseen domains. Results show that finetuned GLM retrievers achieve state‑of‑the‑art performance on two multi‑hop benchmarks and generalize better out of domain, while GNN retrievers excel at graph coverage and vector‑search performs best on single‑hop tasks.
arXiv:2607. 07422v1 Announce Type: new Abstract: Logical Multi-Hop Query Answering over Knowledge Graphs (KGs) can be formulated as querying, with an implicit completeness assumption.
SLogic introduces a subgraph-informed approach to logical rule learning for knowledge graph completion, assigning query-dependent scores to rules instead of a single global weight. The framework uses a context-aware scoring function that evaluates the importance of a rule based on the local subgraph around the query’s head entity, aligning with the specificity principle of commonsense reasoning. Experiments on benchmark datasets demonstrate that SLogic performs competitively with other rule-based methods while producing human-readable, query-specific explanations.