HetSheaf applies cellular sheaves and type-conditioned restriction maps to heterogeneous graphs, plus SheafPool for basis-invariant graph-level representations, delivering competitive accuracy with substantially reduced parameter counts.
Embedding Entities and Relations for Learning and Inference in Knowledge Bases
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
We consider learning representations of entities and relations in KBs using the neural-embedding approach. We show that most existing models, including NTN (Socher et al., 2013) and TransE (Bordes et al., 2013b), can be generalized under a unified learning framework, where entities are low-dimensional vectors learned from a neural network and relations are bilinear and/or linear mapping functions. Under this framework, we compare a variety of embedding models on the link prediction task. We show that a simple bilinear formulation achieves new state-of-the-art results for the task (achieving a top-10 accuracy of 73.2% vs. 54.7% by TransE on Freebase). Furthermore, we introduce a novel approach that utilizes the learned relation embeddings to mine logical rules such as "BornInCity(a,b) and CityInCountry(b,c) => Nationality(a,c)". We find that embeddings learned from the bilinear objective are particularly good at capturing relational semantics and that the composition of relations is characterized by matrix multiplication. More interestingly, we demonstrate that our embedding-based rule extraction approach successfully outperforms a state-of-the-art confidence-based rule mining approach in mining Horn rules that involve compositional reasoning.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Feature reconstruction in GSSL is robust to noise in text-driven biomedical graphs while relation reconstruction is sensitive, with bidirectional GNN architectures performing better on noisy data and yielding up to 7% gains over language model baselines.
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.
Entity representations learned from text via link prediction generalize to unseen entities and transfer to classification and retrieval with reported gains of 22% MRR, 16% accuracy, and 8.8% NDCG@10.
GraphStar is a new GNN that adds star nodes and relay attention to achieve non-local representations for node, graph, and link tasks, claiming 2-5% gains over prior SOTA on benchmarks.
EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming baselines on four datasets with linear indexing cost and zero token overhead.
MRCKG combines a multimodal-structural curriculum, cross-modal preservation, and contrastive replay to let multimodal knowledge graphs learn new entities and relations over time without catastrophic forgetting.
TED is a heterogeneous GNN that uses related party transaction groups and hierarchical attention to detect tax evasion, claiming significant outperformance over prior methods on two real tax datasets.
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.
T-TExTS builds a domain ontology into a knowledge graph and tests four embedding methods, finding Node2Vec yields the highest AUC (0.9642-0.9750) while a hybrid embedding balances ranking quality with interpretability across dataset sizes of 98-351 texts.
Semantic field-level re-ranking on FSDM candidates yields 2.5% NDCG@10 and 1.2% NDCG@100 gains on DBpedia-Entity v2.
citing papers explorer
-
T-TExTS (Teaching Text Expansion for Teacher Scaffolding): Enhancing Text Selection in High School Literature through Knowledge Graph-Based Recommendation
T-TExTS builds a domain ontology into a knowledge graph and tests four embedding methods, finding Node2Vec yields the highest AUC (0.9642-0.9750) while a hybrid embedding balances ranking quality with interpretability across dataset sizes of 98-351 texts.