https://rajraghuwansh.github.io/tags/kaggle/KaggleHugoBlox Kit (https://hugoblox.com)en-usTue, 01 Feb 2022 00:00:00 +0000https://rajraghuwansh.github.io/media/icon_hu_fb558a5ed99f547e.pnghttps://rajraghuwansh.github.io/tags/kaggle/https://rajraghuwansh.github.io/projects/link-prediction/Tue, 01 Feb 2022 00:00:00 +0000https://rajraghuwansh.github.io/projects/link-prediction/<p>This project presents our solution for the CentraleSupélec Data Science Kaggle Competition, where we achieved <strong>2nd Place</strong> for the task of <strong>link prediction in citation networks</strong>.</p> <p>The goal of the project was to predict missing links between papers in a citation graph using machine learning and graph-based methods. The task required understanding the structure of citation networks and designing models that could effectively infer whether an edge should exist between two nodes.</p> <p>Our approach focused on leveraging graph representations and learning meaningful relationships between papers based on the network structure. This project highlights the use of <strong>Graph Neural Networks (GNNs)</strong> and related techniques for relational learning on graph data.</p> <p>You can view the full winning solution here:</p> <p> </p>