We are excited to announce the top 3 winners of the IJCNN 2025 Learning with Noisy Graph Labels Competition!ย After careful evaluation, these teams demonstrated outstanding performance on both public and private test sets.
๐ Great job to all the teams who participated!
While Katbam and Interlyze achieved strong scores, they unfortunately did not comply with the official GitHub submission rules, leading to disqualification.
<?> Teams Didn't Qualify for the Evaluation Round
Other teams had very low scores on the publicly available test set, which did not meet the qualification threshold for the evaluation round.
โจ Top three teams have the chance to submit a paper for review, which may be considered for publication in the IJCNN 2025 Proceedings on IEEE Xplore.
๐ Other participants can also submit a 2-to-4 page paper to be considered for a poster presentation at the conference (but will not be included in the proceedings).
๐ Congratulations to all participants for their hard work and dedication! We look forward to seeing your research at IJCNN 2025. ๐
For all partecipants: The deadline for submitting the paper is March 9th.
โจ Top three teams ย can submit a 4-8 pages paper for IJCNN 2025 Proceedings on IEEE Xplore.
๐ Other participants can also submit a 2-to-4 page paper to be considered for a poster presentation at the conference (but will not be included in the proceedings).
The paper has to be written ย according to the usual IEEE conference template used by the IJCNN 2025 conference (see https://2025.ijcnn.org/authors/initial-author-instructions).ย
In case you are interested these are the instructionsย for the submission:
Access https://cmt3.research.microsoft.com/IJCNN2025/Submission/Indexย
Log in with your credential or create a new account, then select "Create a new Submission" and choose "Competition Track" as for SUBJECT AREAS select "Learning with Noisy Graph Labels".