The use of Machine Learning is well-established for modalities such as text, images, audio, and even video. In the past years, a less studied modality is structured data, such as relational tables and knowledge graphs. Recent works attempt to use this modality as part of, or in combination with, ML models. This workshop will host a program focused on representation learning and generative models for structured data, such as relational tables and spreadsheets, as well as knowledge graphs. The workshop will also engage researchers focusing on the intersection of learning over structured data and information retrieval, for example, in retrieval augmented generation (RAG) and question answering (QA) systems. The aim of the workshop is to connect researchers working on this topic and surface novel research ideas and collaboration opportunities by bringing views from the NLP, ML, DB, and IR disciplines together.

We welcome extended abstracts that will be presented as a poster. We might invite a few selected abstracts for a spotlight talk.

• Submission format: we invite extended abstracts of 2 pages (excl. references).

• Submission template: LNCS template (https://www.overleaf.com/latex/templates/springer-lecture-notes-in-computer-science/kzwwpvhwnvfj)

• Submission portal: https://openreview.net/group?id=ELLIS.eu/2024/Workshop/RLGMSD

• Extended Abstract submission: 31 January 2025 -> due to the ICML deadline, extended to 3 February 2025 (6PM CET)

• Notification: 4 February 2025

• Workshop: 27 February 2025

• Iacer Calixto (UvA, Amsterdam UMC)

• Michael Cochez (VU)

• Madelon Hulsebos (CWI)

• Andrew Yates (UvA)

The program is expected to start around 9:30AM (walk-in from 9:00AM) and last until roughly 5:30-6:00PM CET.