KGEMs for link prediction exhibit high instability in predictions and embeddings from initialization, negative sampling, and other factors, with better MRR not ensuring higher stability.
hub
In: Proceedings of the AAAI Conference on Artifi- cial Intelligence, vol
6 Pith papers cite this work, alongside 3,648 external citations. Polarity classification is still indexing.
6
Pith papers citing it
3,648
external citations · Crossref
hub tools
representative citing papers
PARK personalizes academic search by embedding a citation-derived knowledge graph into the same vector space as a neural retrieval model, beating baselines in three of four domains.
Authors release the multimodal WJoconde knowledge graph for French cultural heritage and a LLM-VLM pipeline that extracts and validates new triples from unstructured text and images to extend the graph.
SARMP improves knowledge graph link prediction by selecting the Top-K semantically relevant edges per node and aggregating them with multi-head attention, beating some baselines on FB15k-237 and Kinship but not all benchmarks.
Encoding higher-order structures as heterogeneous property graphs lets standard graph databases support hyperedges, node-tuples, and subgraphs; a Neo4j-based prototype, ACID discussion, complexity analysis, and a GNN accuracy demonstration are presented.
A bidirectional decoder with a graph-aware attention mask, knowledge-masked prediction, and contrastive sub-graph alignment achieves reported state-of-the-art link prediction on Wikidata5M and competitive results on WN18RR.
citing papers explorer
-
Multimodal Cultural Heritage Knowledge Graph Extension with Language and Vision Models
Authors release the multimodal WJoconde knowledge graph for French cultural heritage and a LLM-VLM pipeline that extracts and validates new triples from unstructured text and images to extend the graph.
-
Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing
SARMP improves knowledge graph link prediction by selecting the Top-K semantically relevant edges per node and aggregating them with multi-head attention, beating some baselines on FB15k-237 and Kinship but not all benchmarks.