Outreach

Watch below some of our videos at conferences and seminars, where members of our group present highlights from our list of publications.

You can also listen to podcasts featuring Dr. Rebekka Burkholz (some are in German and some in English).

We also share other links to interesting articles, interviews, and more.

Videos

Celia Rubio-Madrigal @ Cohere Labs (Feb 13, 2025)

Rewiring Graph Neural Networks: When Less is More and Structure Matters

Based on papers:

  • Spectral Graph Pruning Against Over-Squashing and Over-Smoothing, Adarsh Jamadandi*, Celia Rubio-Madrigal*, and Rebekka Burkholz, NeurIPS 2024. (Link to paper)
  • GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring, Celia Rubio-Madrigal*, Adarsh Jamadandi*, and Rebekka Burkholz, ICLR 2025. (Link to paper)

Rebekka Burkholz @ Labroots (Jul 16, 2024)

Modelling the Accumulation of Mutations During Cancer Progression without Explicit Time

Based on papers:

  • Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification, Alkis Gotovos, Rebekka Burkholz, John Quackenbush, and Stefanie Jegelka, NeurIPS 2021. (Link to paper)

Celia Rubio-Madrigal @ HAICON (Jun 14, 2024)

Can Graph Attention Networks Learn the Degree to Which Node Properties Are Determined by Their Neighborhood?

Based on papers:

  • Are GATs Out of Balance?, Nimrah Mustafa, Aleksandar Bojchevski, and Rebekka Burkholz, NeurIPS 2023. (Link to paper)
  • GATE: How to Keep Out Intrusive Neighbors, Nimrah Mustafa, and Rebekka Burkholz, ICML 2024. (Link to paper)

Rebekka Burkholz @ CRC 1461 Neurotronics Colloquium (Apr 25, 2024)

Can Deep Learning Succeed at Small Scales?

Deep learning continues to achieve impressive breakthroughs across disciplines but relies on increasingly large neural network models that are trained on massive data sets. Their development inflicts costs that are only affordable by a few labs and prevent global participation in the creation of related technologies. In this talk, we will ask the question if it really has to be like this and discuss some of the major challenges that limit the success of deep learning on smaller scales. We will give three examples of complimentary approaches that could help us address the underlying issues: (i) early neural network sparsification, (ii) the integration of useful inductive bias in the design of problem specific neural network architectures (with biomedical applications), and (iii) the improvement of training from scratch in the context of graph neural networks.

Rebekka Burkholz @ One World ML (Feb 8, 2023)

Pruning Deep Neural Networks for Lottery Tickets

Based on papers:

  • On the Existence of Universal Lottery Tickets, Rebekka Burkholz, Nilanjana Laha, Rajarshi Mukherjee, and Alkis Gotovos, ICLR 2022. (Link to paper)
  • Plant 'n' Seek: Can You Find the Winning Ticket?, Jonas Fischer, and Rebekka Burkholz, ICLR 2022. (Link to paper)
  • Convolutional and Residual Networks Provably Contain Lottery Tickets, Rebekka Burkholz, ICML 2022. (Link to paper)
  • Most Activation Functions Can Win the Lottery Without Excessive Depth, Rebekka Burkholz, NeurIPS 2022. (Link to paper)

Rebekka Burkholz @ FutureofHealthTech (FHTI at MIT) (Dec 21, 2019)

Non-invasive Diagnosis of a Rare Heart Disease

Based on papers:

  • Artificial Intelligence in Echocardiography Diagnostics – Detection of Takotsubo Syndrome, D Di Vece, F Laumer, M Schwyzer, R Burkholz, L Corinzia, V.L Cammann, R Citro, J Bax, J.R Ghadri, J.M Buhmann, C Templin, European Heart Journal, Volume 41, 2020. (Link to paper)

Link: https://youtu.be/6ZD9TZlngj0

Podcasts

Rebekka Burkholz @ detektor.fm (Jun 19, 2025)

Demokratie statt Datenmonopol

Große KI-Modelle wie ChatGPT brauchen riesige Rechenzentren und jede Menge Energie und werden fast ausschließlich von Tech-Giganten entwickelt. Welche Vorteile hätte es, Deep Learning zu demokratisieren? Und wie können kleinere KI-Modelle dazu beitragen, die Abhängigkeit von großen Tech-Konzernen zu reduzieren? Wie man Deep Learning demokratisieren kann, das erforscht Dr. Rebekka Burkholz am CISPA Helmholtz-Zentrum für Informationssicherheit. Im „Forschungsquartett“-Gespräch mit detektor.fm-Redakteurin Esther Stephan erklärt sie, warum das notwendig ist, und wieso kleinere KI-Modelle vielleicht sogar besser sind.

Rebekka Burkholz @ CISPA TL;DR (Aug 29, 2024)

Maschinelles Lernen und Künstliche Intelligenz

Runde 2 unserer Sommer-Konferenz-Reihe: auf der ICML in Wien haben wir uns mit Rebekka Burkholz hingesetzt um über ihre Forschung und das Neueste im Bereich des maschinellen Lernens zu sprechen. Rebekka kam 2021 zum CISPA kam und ist seitdem mit einem ERC-Starting Grant ausgezeichnet worden, um mit ihrer Forschung neuronale Netzwerke effizienter zu machen. Im Podcast sprechen wir darüber, wie sie ihren wissenschaftlichen Hintergrund aus der Physik im Bereich KI anwendet und wie KI in Zukunft die Gesellschaft beeinflussen kann.

Rebekka Burkholz @ Scholarly Communication (Mar 8, 2024)

My Leadership Style is ‘We-Learn-Together’

Listen to this interview of Rebekka Burkholz, faculty at the CISPA Helmholtz Center for Information Security. We talk about the composition of research groups and of research papers. Rebekka Burkholz: “I have the feeling that this meta-reading becomes more important as a person’s career progresses. Because early on, a researcher is typically very focused on the details of each paper and they try to understand what this method does and so on — and of course, researchers need to begin that way, really spending the time to attain to expertise in a particular focus. But with time, as a researcher has seen more ideas (and of course, in one particular focus, methods and questions all share some similarity), then the person acquires more and more overview as they continue reading. They are reading, essentially, for the links between findings, for implications of the findings and those links — and in this way, a more experienced reader of the research actually becomes engaged in a sort of literature discussion.”

Rebekka Burkholz & Julian Loss @ CISPA TL;DR (Nov 2, 2023)

Two ERC Starting Grants for Dr. Rebekka Burkholz & Dr. Julian Loss

Dr. Rebekka Burkholz and Dr. Julian Loss seem to have liked it on our podcast – they both are returning for their second episode of TL;DR! The two CISPA Faculty are working on completely different things, but they both have been awarded with a prestigious research grant by the European Research Council (ERC) this fall: the ERC Starting Grant. We talk about what it means for them to receive this grant, what their research has in common and how to facilitate interdisciplinary research. Now available at all your favorite podcast platforms!

Rebekka Burkholz @ CISPA TL;DR (Dec 7, 2022)

Maschinelles Lernen mit Dr. Rebekka Burkholz

CISPA-Faculty Dr. Rebekka Burkholz spricht in dieser Folge mit uns darüber, was relationales maschinelles Lernen ist und welche Chancen Methoden des maschinellen Lernens in der Diagnostik und Behandlung von Krankheiten eröffnen. Die Mathematikerin gibt zudem Einblicke, was Informatiker:innen und Mathematiker:innen unterscheidet und was aus ihrer Sicht helfen würde, mehr Frauen für eine Karriere in der Forschung zu begeistern.

NetBioMed 2025 Keynote (Jun 2, 2025)

After coffee break we had Rebekka Burkholz discussing current challenges when modelling gene regulation and how to fix them. Her approach is innovative and allows us to infer biological processes with both scalability and interpretability.

Link: https://bsky.app/profile/netbiomed2025.bsky.social/post/3lqmzjkcks22l

Die Abenteuer der KI in der Genomik (Jun 19, 2024)

Beim Berlin Summer Meeting am MDC-BIMSB trafen sich Molekularbiolog*innen und Bioinformatiker*innen, um die neuesten Erfolge und Herausforderungen zu diskutieren. Sie loteten aus, wie sie Künstliche Intelligenz am besten für die Biomedizin nutzen können.

Link: https://www.mdc-berlin.de/de/news/news/die-abenteuer-der-ki-der-genomik