[VU ML Seminar] Next meeting: Erkan Karabulut on Scalable Neurosymbolic Knowledge Discovery

[Erkan Karabulut]

Dear All,

Thank you for coming to my talk today and I apologize for the really long 20 minutes delay due to the screen needing a restart.

I hope you found it interesting and please find my slides attached.

I am open for collaborations on any of the directions I presented or any others if you think it might be relevant.

Kind regards,
Erkan
________________________________
From: Vu.ml.seminar.beta <vu.ml.seminar.beta-bounces at listserver.vu.nl> on behalf of Daza Cruz, D.F. (Daniel) via Vu.ml.seminar.beta <vu.ml.seminar.beta at listserver.vu.nl>
Sent: Wednesday, December 3, 2025 3:14 PM
To: _list_vu.ml.seminar.beta <vu.ml.seminar.beta at listserver.vu.nl>
Subject: [VU ML Seminar] Next meeting: Erkan Karabulut on Scalable Neurosymbolic Knowledge Discovery

Dear colleagues,

We are pleased to invite you to the next meeting of the VU ML Seminar<https://sites.google.com/view/vumls/home>. This is also the last meeting of the year before we go on an end-of-year break.

Our next speaker is Erkan Karabulut, who will talk about Scalable Neurosymbolic Knowledge Discovery from Tabular Data.

Erkan is a PhD candidate at the Intelligent Data Engineering Lab<https://indelab.org/> at the University of Amsterdam, and currently he is doing a research visit at Amsterdam UMC.

Abstract:
Discovering patterns from data in human-understandable forms is a valuable task for both knowledge discovery and interpretable inference. A prominent method is Association Rule Mining (ARM), which identifies patterns in the form of logical rules describing relationships between data attributes. Popular ARM methods, however, rely on algorithmic or optimization-based solutions that struggle to scale to high-dimensional datasets (i.e., tables with many columns) without effective search space reduction.

This talk introduces Aerial+, a novel ARM method that leverages neural networks’ ability to handle high-dimensional data to learn a concise set of prominent patterns from tabular datasets. Aerial+ has been evaluated on both digital twin datasets (sensor data enriched with semantics) and on generic tabular datasets, demonstrating its versatility across domains. In addition, Aerial+ can incorporate prior knowledge to enhance discovery: either from knowledge graphs (structured semantic information about a domain) or from tabular foundation models, large pre-trained neural networks that capture table semantics and support diverse downstream tasks.



The meeting will take place on Monday 8 Dec. at 10:00 in room NU-3A57. We hope to see many of you there!

The organizers,

Daniel  & Zhao


---
VU ML Seminar | Schedule: sites.google.com/view/vumls/home
Manage your subscription: listserver.vu.nl/mailman/options/vu.ml.seminar.beta

______________________________________________________
AmsterdamUMC disclaimer : www.amsterdamumc.org/nl/disclaimers.htm
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://listserver.vu.nl/pipermail/vu.ml.seminar.beta/attachments/20251208/d12f1bbf/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: VU ML Seminar.pdf
Type: application/pdf
Size: 3469896 bytes
Desc: VU ML Seminar.pdf
URL: <https://listserver.vu.nl/pipermail/vu.ml.seminar.beta/attachments/20251208/d12f1bbf/VUMLSeminar-0001.pdf>