https://github.com/lirt1231/degreembed
공식 코드DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Link Prediction is a task in graph and network analysis where the goal is to predict missing or future connections between nodes in a network. Given a partially observed network, the goal of link prediction is to infer which links are most likely to be added or missing based on the observed connections and the structure of the network.
<span style="color:grey; opacity: 0.6">( Image credit: Inductive Representation Learning on Large Graphs )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning
KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformation
Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphs
On Calibration of Graph Neural Networks for Node Classification
TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs
Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
DeepHGCN: Toward Deeper Hyperbolic Graph Convolutional Networks
Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation
NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion
Prix-LM: Pretraining for Multilingual Knowledge Base Construction
Improving Temporal Link Prediction via Temporal Walk Matrix Projection
UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
Automated Cognate Detection as a Supervised Link Prediction Task with Cognate Transformer
MGCN: Semi-supervised Classification in Multi-layer Graphs with Graph Convolutional Networks
Improving Inductive Link Prediction Using Hyper-Relational Facts
ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations
Composition-based Multi-Relational Graph Convolutional Networks
Neural Graph Embedding Methods for Natural Language Processing
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
Two-stage Training of Graph Neural Networks for Graph Classification
Perception-Inspired Graph Convolution for Music Understanding Tasks
Graph Convolutional Networks for Graphs Containing Missing Features
MPXGAT: An Attention based Deep Learning Model for Multiplex Graphs Embedding
ReInform: Selecting paths with reinforcement learning for contextualized link prediction
Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.