Download PDFOpen PDF in browserMAT: Effective Link Prediction via Mutual Attention TransformerEasyChair Preprint 114644 pages•Date: December 6, 2023AbstractThe Data Science and Advanced Analytics (DSAA) 2023 challenge[1] focuses on proposing link prediction methods to solve challenges about network-like data structure such as network reconstruction, network development, etc from articles on Wikipedia. In this challenge, we propose the Mutual Attention Transformer (MAT) method to predict if there is a link between two Wikipedia pages. Our method achieved the 5th and 4th position on the leaderboard for the public test and private test, respectively. Code will be publicly available for the ease of experimental re-implementation Keyphrases: attention, link prediction, transformer
|