Knowledge Tree
link prediction
Facts (35)
Sources
Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org 12 facts
claimThe Drug Repurposing Knowledge Graph (DRKG) applies link prediction using graph embeddings with the TransE model to predict relations between drugs, genes, and the diseases SARS, MERS, and SARS-COV2 (COVID-19).
claimLink prediction is a task in knowledge graph construction that aims to identify missing relations between entities, such as identifying that the song 'Ageispolis' was written by the artist 'Aphex Twin'.
claimEmbedding-based link prediction methods that rely on shallow embeddings store all embeddings in an entity/relation matrix and retrieve them via a lookup table, which prevents these models from handling unseen entities.
claimBlevins et al. propose a link prediction approach that learns patterns from entire Wikipedia articles.
claimLange et al. utilize Conditional Random Fields to learn patterns for link prediction based on Wikipedia abstracts.
claimIn addition to construction tools, the HKGB platform provides three graph tools for data discovery, extraction, and link prediction to support domain-related applications.
formulaThe TransE model performs link prediction by encoding relations as translations from a subject entity to an object entity, minimizing the distance between the subject embedding plus the relation embedding and the object embedding.
claimThe DRKG, HKGB, and SAGA knowledge graph construction solutions use machine learning-based link prediction on graph embeddings to find further knowledge for knowledge completion.
claimCurrent approaches for Knowledge Graph completion typically limit themselves to a single task, such as determining missing type information, missing relations (link prediction), or missing attribute values, and lack holistic solutions to simultaneously improve the quality of knowledge graphs in several areas.
claimNodePiece allows the use of any scoring function, such as TransE, for link prediction tasks because it can create entity representations for unseen entities that have known relations.
procedureDistant supervision is a common method for link prediction that involves linking knowledge graph entities to a text corpus using NLP approaches and identifying patterns between those entities within the text.
claimKnowledge graph embeddings encode entities and relations as low-dimensional vectors in an embedding space to facilitate link prediction.
Knowledge Graphs: Opportunities and Challenges - Springer Nature link.springer.com Apr 3, 2023 5 facts
measurementIn performance evaluations based on link prediction and triplet classification tasks, models including QuatE (90%), RMNN (89.9%), and KBGAN (89.2%) achieved impressive results using the Hits@10 and accuracy metrics.
procedureKnowledge graph completion aims to expand existing knowledge graphs by adding new triplets using techniques for link prediction (Wang et al. 2020b; Akrami et al. 2020) and entity prediction (Ji et al. 2021).
procedureKnowledge graph completion typically utilizes link prediction techniques to generate triplets and subsequently assigns plausibility scores to those triplets (Ji et al. 2021).
referenceNayyeri et al. (2021) published 'Trans4e: link prediction on scholarly knowledge graphs' in Neurocomputing 461:530–542, which introduces a method for link prediction specifically applied to scholarly knowledge graphs.
claimTemporal knowledge graph completion methods improve link prediction accuracy by integrating timestamps into the learning process to account for the validity of knowledge over time.
Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org Feb 16, 2025 4 facts
claimGraph Neural Networks (GNNs) are used for tasks including link prediction, node classification, recommendation systems, and knowledge graph reasoning.
claimReasoning and inference methods, such as chain-of-thought (CoT) reasoning and link prediction, enhance the logical decision-making capabilities of AI systems.
claimMethods such as Graph Neural Networks (GNNs), Named Entity Recognition (NER), link prediction, and relation extraction fall into the Neuro[Symbolic] category because they leverage symbolic relationships like ontologies or graphs to enhance neural processing.
referenceNeuSTIP combines Graph Neural Network (GNN)-based neural processing with symbolic reasoning to tackle link prediction and time interval prediction in temporal knowledge graphs (TKGs).
Neuro-Symbolic AI: Explainability, Challenges, and Future Trends arxiv.org Nov 7, 2024 3 facts
referenceSingh et al. (2023) introduced NeuSTIP, a neuro-symbolic model designed for link and time prediction in temporal knowledge graphs.
claimLemos et al. (2020) proposed a neural symbolic model designed for relational reasoning and link prediction on knowledge graphs.
referenceAriam Rivas, Diego Collarana, Maria Torrente, and Maria-Esther Vidal developed a neuro-symbolic system that utilizes knowledge graphs for link prediction, as detailed in their 2022 Semantic Web Preprint.
Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org 2 facts
referenceKim et al. (2020) integrate relation prediction and relevance ranking tasks with link prediction to improve the learning of relational attributes in knowledge graphs.
referenceBiswas, Sack, and Alam (2024) introduced MADLINK, a method using attentive multihop and entity descriptions for link prediction in knowledge graphs, published in Semantic Web.
A survey on augmenting knowledge graphs (KGs) with large ... link.springer.com Nov 4, 2024 2 facts
referenceThe Open Graph Benchmark (OGB) is a collection of large-scale datasets for machine learning on graphs, covering tasks such as node classification, link prediction, and graph classification.
referenceWikiKG90M is a large-scale benchmark used to evaluate knowledge graph completion tasks, specifically link prediction and entity classification.
KG-IRAG: A Knowledge Graph-Based Iterative Retrieval-Augmented ... arxiv.org Mar 18, 2025 2 facts
claimLarge Language Models (LLMs) contribute to knowledge graph completion, specifically aiding in downstream tasks such as node classification and link prediction.
referenceDong Shu, Tianle Chen, Mingyu Jin, Yiting Zhang, Mengnan Du, and Yongfeng Zhang authored 'Knowledge graph large language model (kg-llm) for link prediction', published as an arXiv preprint (arXiv:2403.07311).
Combining large language models with enterprise knowledge graphs frontiersin.org Aug 26, 2024 1 fact
claimModeling Knowledge Graph Embedding (KGE) as a classification problem prevents the correct handling of Knowledge Graphs (KGs) where multiple relations connect two entities, negatively affecting both disambiguation and link prediction.
Empowering RAG Using Knowledge Graphs: KG+RAG = G-RAG neurons-lab.com 1 fact
referenceGraph Neural Networks (GNNs) are specialized for graph-structured data and enhance Knowledge Graphs by capturing direct and indirect relationships, propagating information across graph layers to learn rich representations, and generalizing to various graph types for tasks like node classification and link prediction.
The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org Jul 11, 2024 1 fact
claimGraph Neural Networks (GNNs) excel in tasks such as node classification, link prediction, and the extraction of hidden patterns from graph-structured data.
Medical Hallucination in Foundation Models and Their Impact on ... medrxiv.org Nov 2, 2025 1 fact
claimResearchers have explored methodologies to incorporate Knowledge Graphs into Large Language Model workflows to improve factual accuracy in tasks such as link prediction, rule learning, and downstream polypharmacy (reference 65).
Medical Hallucination in Foundation Models and Their ... medrxiv.org Mar 3, 2025 1 fact
claimGema et al. (2024) explored methodologies to incorporate Knowledge Graphs (KGs) into Large Language Model (LLM) workflows to improve factual accuracy in tasks such as link prediction, rule learning, and downstream polypharmacy.