Data Science Competition

DSAA-2023 conference includes a data science competition, aiming at proposing effective and efficient solutions for the link prediction task. More specifically, given an input graph G, some of the edges of G have been removed and the resulting graph is termed G’. Given some pairs of nodes from G’, we need to decide if there is an edge between the node pairs in the original graph G. The dataset used in the contest is extracted from Wikipedia, where graph nodes are annotated with text.

The competition is hosted by Kaggle. You can participate by following the link below:

By June 30, teams are requested to provide the source code of their solutions as well as a short report (max 4 pages, IEEE 2-column style) describing their solution, algorithmic techniques used (unsupervised, supervised, semi-supervised), libraries used, runtime required for model training and testing, a description of the hardware used, as well as any other information related to the score achieved in Kaggle. The above report should be submitted as a “regular” paper at the proper track of DSAA-2023 at Easychair.

The top-5 teams will have the opportunity to present their work at a conference special session, whereas their papers will be included in the IEEE Proceedings. A conference registration is required for the papers to be included in the program and the proceedings. Awards are planned for the top-3 teams.

  • Start of contest April 21, 2023
  • End of contest June 28, 2023
  • Submission of reports June 30, 2023
  • Notification July 15, 2023
  • Camera-ready August 7, 2023 (also, registration deadline)