Papers with Code 아카이브
Knowledge Graph Completion
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 7
- 보존된 평가 기록
- 17
Knowledge graphs $G$ are represented as a collection of triples $\\{(h, r, t)\\}\subseteq E\times R\times E$, where $E$ and $R$ are the entity set and relation set. The task of Knowledge Graph Completion is to either predict unseen relations $r$ between two existing entities: $(h, ?, t)$ or predict the tail entity $t$ given the head entity and the query relation: $(h, r, ?)$.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/thunlp/OpenKE
공식 코드https://github.com/tongzhou21/CogMG
공식 코드CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph
https://github.com/tranhungnghiep/KG20C
공식 코드Exploring Scholarly Data by Semantic Query on Knowledge Graph Embedding Space
https://github.com/tranhungnghiep/MEI-KGE
공식 코드Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion
https://github.com/tsafavi/cascader
공식 코드CascadER: Cross-Modal Cascading for Knowledge Graph Link Prediction
https://github.com/tsafavi/codex
공식 코드https://github.com/ttrouill/complex
공식 코드https://github.com/txsun1997/CoLAKE
공식 코드https://github.com/uma-pi1/grash
공식 코드Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings
https://github.com/usail-hkust/urbankgent
공식 코드UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction
https://github.com/vid-koci/kbctransferlearning
공식 코드Pre-training and Diagnosing Knowledge Base Completion Models
https://github.com/vinhsuhi/wge
공식 코드Two-view Graph Neural Networks for Knowledge Graph Completion
https://github.com/vivian1993/ncrl
공식 코드Neural Compositional Rule Learning for Knowledge Graph Reasoning
https://github.com/wangbo9719/StAR_KGC
공식 코드Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion
https://github.com/wangpf3/LAN
공식 코드Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding
https://github.com/wangskyGit/KeHGN-R
공식 코드https://github.com/weiyanbin1999/kicgpt
공식 코드KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion
https://github.com/wentao-xu/kge-cl
공식 코드KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings
https://github.com/wjk666/disenkgat
공식 코드DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network
https://github.com/wylresearch/kc-genre
공식 코드https://github.com/wzh-nlp/ookg
공식 코드Iteratively Learning Representations for Unseen Entities with Inter-Rule Correlations
https://github.com/xiaomingaaa/sdn
공식 코드S$^2$DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion
https://github.com/xincanfeng/dimension
공식 코드Sharing Parameter by Conjugation for Knowledge Graph Embeddings in Complex Space
https://github.com/xincanfeng/ms_kge
공식 코드https://github.com/xjtuwgt/gnn-magna
공식 코드https://github.com/xwhan/DeepPath
공식 코드DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
https://github.com/xwhan/One-shot-Relational-Learning
공식 코드https://github.com/yao8839836/kg-bert
공식 코드https://github.com/yao8839836/kg-llm
공식 코드Exploring Large Language Models for Knowledge Graph Completion
https://github.com/yifan-h/multilingual_space
공식 코드Adapters for Enhanced Modeling of Multilingual Knowledge and Text
https://github.com/yihong-chen/refactorgnn
공식 코드ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
https://github.com/yihuazhu111/orthogonale
공식 코드Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding
https://github.com/yizhilll/transher
공식 코드TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction
https://github.com/yuanyehome/palt
공식 코드PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion
https://github.com/yuchengz99/trix
공식 코드TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.