Results 11 to 20 of about 6,752,678 (299)
Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction [PDF]
Neural Information Processing Systems, 2022 Graph Neural Networks (GNNs) have been widely applied to various fields for learning over graph-structured data. They have shown significant improvements over traditional heuristic methods in various tasks such as node classification and graph ...
Seongjun Yun +4 more
semanticscholar +1 more source
PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction [PDF]
The Web Conference, 2023 Transparency and accountability have become major concerns for black-box machine learning (ML) models. Proper explanations for the model behavior increase model transparency and help researchers develop more accountable models. Graph neural networks (GNN)
Shichang Zhang +6 more
semanticscholar +1 more source
Graph Neural Networks for Link Prediction with Subgraph Sketching [PDF]
International Conference on Learning Representations, 2022 Many Graph Neural Networks (GNNs) perform poorly compared to simple heuristics on Link Prediction (LP) tasks. This is due to limitations in expressive power such as the inability to count triangles (the backbone of most LP heuristics) and because they ...
B. Chamberlain +7 more
semanticscholar +1 more source
A Theory of Link Prediction via Relational Weisfeiler-Leman [PDF]
Neural Information Processing Systems, 2023 Graph neural networks are prominent models for representation learning over graph-structured data. While the capabilities and limitations of these models are well-understood for simple graphs, our understanding remains incomplete in the context of ...
Xingyue Huang +3 more
semanticscholar +1 more source
Revisiting Link Prediction: A Data Perspective [PDF]
International Conference on Learning Representations, 2023 Link prediction, a fundamental task on graphs, has proven indispensable in various applications, e.g., friend recommendation, protein analysis, and drug interaction prediction. However, since datasets span a multitude of domains, they could have distinct
Haitao Mao +8 more
semanticscholar +1 more source
Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs [PDF]
International Joint Conference on Artificial Intelligence, 2022 Inductive link prediction for knowledge graph aims at predicting missing links between unseen entities, those not shown in training stage. Most previous works learn entity-specific embeddings of entities, which cannot handle unseen entities.
Xiaohan Xu +4 more
semanticscholar +1 more source
Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs [PDF]
AAAI Conference on Artificial Intelligence, 2021 Inductive link prediction---where entities during training and inference stages can be different---has been shown to be promising for completing continuously evolving knowledge graphs.
Jiajun Chen +3 more
semanticscholar +1 more source
Pairwise link prediction [PDF]
Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2019 Link prediction is a common problem in network science that transects many disciplines. The goal is to forecast the appearance of new links or to find links missing in the network. Typical methods for link prediction use the topology of the network to predict the most likely future or missing connections between a pair of nodes.
Nassar, Huda +2 more
openaire +2 more sources
Deep Link-Prediction Based on the Local Structure of Bipartite Networks
Entropy, 2022 Link prediction based on bipartite networks can not only mine hidden relationships between different types of nodes, but also reveal the inherent law of network evolution. Existing bipartite network link prediction is mainly based on the global structure
Hehe Lv +3 more
doaj +1 more source
Link Prediction in Complex Networks: A Survey [PDF]
arXiv.org, 2010 Link prediction in complex networks has attracted increasing attention from both physical and computer science communities. The algorithms can be used to extract missing information, identify spurious interactions, evaluate network evolving mechanisms ...
Linyuan Lu, Tao Zhou
semanticscholar +1 more source