More Like this

1. Link cobordisms and functoriality in link Floer homology

   https://doi.org/10.1112/topo.12085  

   Zemke, Ian (October 2018, Journal of Topology)
2. Group Link Prediction

   https://doi.org/10.1109/BigData47090.2019.9006261  

   Stanhope, Andrew; Sha, Hao; Barman, Danielle; Hasan, Mohammad Al; Mohler, George (December 2019, 2019 IEEE International Conference on Big Data (Big Data))
3. Learning to Link

   Balcan, Maria-Florina; Dick, Travis; Lang, Manuel (April 2020, International Conference on Learning Representation)

   null (Ed.)
4. A k-Means Algorithm for Clustering with Soft Must-link and Cannot-link Constraints [A k-Means Algorithm for Clustering with Soft Must-link and Cannot-link Constraints]

   https://doi.org/10.5220/0010800000003122  

   Baumann, Philipp; Hochbaum, Dorit (January 2022, the 11th International Conference on Pattern Recognition Applications and Methods)
5. PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction

   https://doi.org/10.1145/3543507.3583511  

   Zhang, Shichang; Zhang, Jiani; Song, Xiang; Adeshina, Soji; Zheng, Da; Faloutsos, Christos; Sun, Yizhou (April 2023, WWW '23: Proceedings of the ACM 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) have recently shown superior performance in many graph ML problems than traditional methods, and explaining them has attracted increased interest. However, GNN explanation for link prediction (LP) is lacking in the literature. LP is an essential GNN task and corresponds to web applications like recommendation and sponsored search on web. Given existing GNN explanation methods only address node/graph-level tasks, we propose Path-based GNN Explanation for heterogeneous Link prediction (PaGE-Link) that generates explanations with connection interpretability, enjoys model scalability, and handles graph heterogeneity. Qualitatively, PaGE-Link can generate explanations as paths connecting a node pair, which naturally captures connections between the two nodes and easily transfer to human-interpretable explanations. Quantitatively, explanations generated by PaGE-Link improve AUC for recommendation on citation and user-item graphs by 9 - 35% and are chosen as better by 78.79% of responses in human evaluation. 

   more » « less