https://github.com/ant-research/KnowledgeGraphEmbeddingsViaPairedRelationVectors_PairRE
Open Graph Benchmark: Datasets for Machine Learning on Graphs
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
A knowledge graph is a structured representation of information that organizes data into nodes (entities) and edges (relationships) to show how different pieces of knowledge are interconnected. It enables enhanced data integration, search, and inference by modeling the relationships between concepts and entities in a graph format.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Open Graph Benchmark: Datasets for Machine Learning on Graphs
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
K-BERT: Enabling Language Representation with Knowledge Graph
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
EL Embeddings: Geometric construction of models for the Description Logic EL ++
Investigating Pretrained Language Models for Graph-to-Text Generation
Learning Sequence Encoders for Temporal Knowledge Graph Completion
Open Graph Benchmark: Datasets for Machine Learning on Graphs
BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization
A survey of embedding models of entities and relationships for knowledge graph completion
TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation
Open Graph Benchmark: Datasets for Machine Learning on Graphs
Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
Text Generation from Knowledge Graphs with Graph Transformers
OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.