Papers with Code 아카이브
Link Prediction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 6
- 평가표
- 79
- 보존된 평가 기록
- 497
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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
FedRule: Federated Rule Recommendation System with Graph Neural Networks
Self-Supervised Graph Structure Refinement for Graph Neural Networks
Holder Recommendations using Graph Representation Learning & Link Prediction
Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces
Rethinking the positive role of cluster structure in complex networks for link prediction tasks
KGLM: Integrating Knowledge Graph Structure in Language Models for Link Prediction
An Empirical Study on Data Leakage and Generalizability of Link Prediction Models for Issues and Commits
Search to Pass Messages for Temporal Knowledge Graph Completion
DyG2Vec: Efficient Representation Learning for Dynamic Graphs
Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion
Line Graph Contrastive Learning for Link Prediction
LaundroGraph: Self-Supervised Graph Representation Learning for Anti-Money Laundering
RulE: Knowledge Graph Reasoning with Rule Embedding
Spiking Variational Graph Auto-Encoders for Efficient Graph Representation Learning
DyCSC: Modeling the Evolutionary Process of Dynamic Networks Based on Cluster Structure
A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges
A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs
Generalized Reciprocal Perspective
Along the Time: Timeline-traced Embedding for Temporal Knowledge Graph Completion
Deep Bidirectional Language-Knowledge Graph Pretraining
Parameter-free Dynamic Graph Embedding for Link Prediction
MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks
Inductive Logical Query Answering in Knowledge Graphs
Linkless Link Prediction via Relational Distillation
SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction
Towards Real-Time Temporal Graph Learning
Geodesic Graph Neural Network for Efficient Graph Representation Learning
Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction
A Framework for Large Scale Synthetic Graph Dataset Generation
TPGNN: Learning High-order Information in Dynamic Graphs via Temporal Propagation
Graph Neural Networks for Link Prediction with Subgraph Sketching
MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction
Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.