This [challenge](https://www.continualcausality.org/challenge/) is part of the 3rd [Continual Causality](https://www.continualcausality.org/) Bridge Program at [AAAI 2025](https://aaai.org/conference/aaai/aaai-25/) held on 25th and 26th February 2025.

A well-known problem encountered by typical machine learning methods is that confounders only present in the training data prevent the model from **generalizing to unseen data**. If a model is trained on datasets one after another in the **continual setting**, certain task-specific confounders could negatively affect model performance more severely compared to a joint setup. This **“continual confounding”** problem is represented by **ConCon**, an image dataset based on CLEVR where confounders differ across tasks. It has been shown that joint training on ConCon is less sensitive to confounding compared to the continual learning setup. 

In this challenge, we invite participants to submit solutions to this Kaggle challenge, together with a corresponding 3-page report, for overcoming the challenges posed by continual confounding. All solutions can be submitted **until January 7, 2025**. Note that we also offer an **early deadline on December 6, 2024**. Any entries submitted until this date will be reviewed in time for people to register with the AAAI early registration deadline and to give more time to deal with possible visa issues.

**Leaderboard:** The leaderboard covers submissions for both the strict and disjoint splits of the dataset (even though evaluation is done on the same test set). As both splits come with different assumptions and challenges, don't feel discouraged from submitting your approach just because others seem to perform better in terms of raw numbers. :)


# Challenge Submission

Participants are required to submit a short report (including a link to their code) through the following Google form:
https://forms.gle/vrwmCYT32TTZ7Eor8

If you have any questions, please contact us at info[at]continualcausality[dot]org.