knowledge graph completion
PulseAugur coverage of knowledge graph completion — every cluster mentioning knowledge graph completion across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New framework uses diffusion models for knowledge graph completion
Researchers have developed a new framework called DMKGC for multi-domain knowledge graph completion. This approach uses conditional diffusion models to generate more informative entity embeddings by transferring knowled…
-
Knowledge Graphs and Vector DBs Combine to Enhance AI Agent Memory
Researchers are exploring new methods to improve knowledge graph completion (KGC) by addressing the limitations of traditional triplet prediction. One approach introduces a relation set completion task (RSC) to infer se…
-
New RelBall model enhances knowledge graph completion with novel relation modeling
Researchers have introduced RelBall, a novel model designed to improve knowledge graph completion by addressing limitations in existing methods. RelBall extends the Rotate3D model by incorporating modulus transformation…
-
New research unifies KGC explanations and tackles graph exploration challenges
Researchers are exploring new methods for knowledge graph completion (KGC) and exploration. One paper proposes a unified taxonomy for post-hoc explanations in KGC to improve reproducibility and evaluation. Another intro…
-
New PROBE framework enhances knowledge graph completion model evaluation
Researchers have introduced PROBE, a novel framework for evaluating knowledge graph completion (KGC) models, addressing limitations in existing metrics. PROBE accounts for predictive sharpness and popularity-bias robust…
-
Q-GNN enhances knowledge graph completion with entity and type awareness
Researchers have developed Q-GNN, a novel approach for knowledge graph completion that enhances reasoning by incorporating information from both the query entity and relation. Unlike previous methods that primarily used…
-
New framework ReaLM fuses KG embeddings with LLMs; study finds KG embedding models unstable
Researchers have developed ReaLM, a new framework that bridges the gap between knowledge graph embeddings and large language models by discretizing KG embeddings into learnable tokens. This approach allows for a more ef…