<div dir="ltr"><p>ICLR 2023 Workshop: What do we need for successful domain generalization?</p><p>Website: <a href="https://domaingen.github.io/">https://domaingen.github.io/</a></p><p>The real challenge for any machine learning system is to be reliable
and robust in any situation, even if it is different compared to
training conditions. Existing general purpose approaches to domain
generalization (DG) — a problem setting that challenges a model to
generalize well to data outside the distribution sampled at training
time — have failed to consistently outperform standard empirical risk
minimization baselines. In this workshop, we aim to work towards
answering a single question: <em>what do we need for successful domain generalization?</em>
We conjecture that additional information of some form is required for a
general purpose learning methods to be successful in the DG setting.
The purpose of this workshop is to identify possible sources of such
information, and demonstrate how these extra sources of data can be
leveraged to construct models that are robust to distribution shift.
Specific topics of interest include, but are not limited to:</p>
* Leveraging domain-level meta-data<br>* Exploiting multiple modalities to achieve robustness to distribution shift<br>* Frameworks for specifying known invariances/domain knowledge<br>* Causal modeling and how it can be robust to distribution shift<br>* Empirical analysis of existing domain generalization methods and their underlying assumptions<br>* Theoretical investigations into the domain generalization problem and potential solutions<div><br></div><div>Submissions are accepted via OpenReview: <a href="https://openreview.net/group?id=ICLR.cc/2023/Workshop/DG">https://openreview.net/group?id=ICLR.cc/2023/Workshop/DG</a></div><div><br></div><div>Submission deadline: February 3, 2023</div><div>
Author notifications: March 3, 2023</div><div>Meeting: May 5, 2023</div></div>