Call for Participation

Submission deadline (non-archival track): January 7, 2024, Anywhere On Earth (AoE). Submission are handled through OpenReview: https://openreview.net/group?id=AAAI.org/2025/Bridge/Continual_Causality

Notifications (non-archival track): January 14, 2024

(passed) Submission deadline (proceedings track): November 25, 2024

Notifications: December 10, 2024

Bridge: February 25+26, 2025

The fields of causality and continual learning investigate complementary aspects of human cognition, and artificial intelligence must emulate both if it is to reason and generalize in complex environments. On the one hand, causality theory provides the language, algorithms, and tools to discover and infer cause-and-effect relationships from data. On the other hand, continual learning systems must balance learning from new data as they become available with retaining previous knowledge of systems that may not be stationary. Our recurring Continual Causality Bridge continues working towards a unified treatment of these fields by providing a space to learn and discuss, and to connect and build a diverse long-term community.

Non-archival track: previously published works and novel works in early stages

New this year: In addition to our traditional proceedings track (moved to the bottom of the page, as the deadline has passed), we will also allow for presentations of recently published works and novel works that are in an earlier stage for non-archival inclusion in our bridge. For already published works, we consider work recent if it has been published at a top tier venue after AAAI-24 (including works that have been accepted to the main track of AAAI-25). These works should be submitted in their original length and template. For novel works that wish to be presented at the bridge in non-archival form for an opportunity to receive feedback, we will consider contributions of 2-4 pages in the AAAI template. Submitted works for the non-archival track will be uploaded to the continual causality website, but generally do not count as publications. They are free to be resubmitted to future venues.

The submission deadline for our non-archival track is January 7th. Submissions of previously accepted papers do not need to be anonymized, whereas novel works should be anonymous. As this track’s focus in community-building and feedback on novel ideas, the review process will be light and inclusive, focusing primarily on technical correctness and fit to the bridge’s themes.

Proceedings track

We invite submissions for a proceedings track that present general positions or visions of how to link the two fields, outline challenges that need to be overcome, highlight synergies, propose tangible future steps, or discuss first practical approaches and solutions to relevant problems. Our vision is for prospective community members to voice diverse views that have the potential to advance AI through an ongoing interdisciplinary exchange. We therefore have no strict constraints on the exact sub-topics of submissions, as long as they target the overall goal of bridging the fields. Submissions are free to focus on a single particularly interesting synergy, take an angle from a specific scientific discipline, or sketch a grander view. To provide some suggestions, contributions could center around the following aspects, including but not limited to:

  • Continual learning and exploitation of causal systems in dynamic non-stationary environments.
  • Catastrophic interference and knowledge transfer in learning causal models in the context of continuous streams of data.
  • Effective ways for causal structure to aid in leveraging the accumulated knowledge of a continual learning system.
  • Leveraging causal tools to interpret distributional shifts in continual learning.
  • Next generation benchmarks that go beyond repurposing of existing datasets to adequately support the above items and further essential research questions towards a symbiosis of continual learning and causality.

Submission will be compiled in a Proceedings of Machine Learning Research (PMLR) volume. Works must be original and limited to four pages (excluding references and optional appendices) in the AAAI format. The deadline for submissions is November 25, 2024 (AOE). All submissions will be managed through OpenReview. The review process is double-blind, so submissions should be anonymized.

Continual Confounding Challenge

We are further hosting a continual confounding challenge, for which we encourage contributions as specified in the respective challenge tab on the website.

For further questions join our Slack or Email the organizers at info[at]continualcausality[dot]org