About

Welcome to my website. I am a final-year PhD candidate in the Exploratory Data Analysis group at the CISPA Helmholtz Center for Information Security and a guest researcher in the department for Algorithms & Complexity at the Max Planck Institute for Informatics.
I am broadly interested in topics related to machine learning, data mining, and optimization, where I seek to develop methods that are theoretically sound yet practically useful, especially for the natural sciences. My Ph.D. research focuses on identifying and characterizing groups in scientific datasets and networks. Recently, I have worked on statistically significant pattern mining, graph analysis, matrix factorization, and hypergraph curvature. Apart from doing science, I enjoy hiking, music, and apple pie.
I will be on the job market soon.

Research Interests

• Machine Learning and Data Mining
• Machine Learning for Science
• Mathematical Optimization

Education

• Ph.D. Student at CISPA Helmholtz Center for Information Security
• Master of Computer Science (M.Sc.) at Saarland University
• Bachelor of Computer Science (B.Sc.) at Philipps-University Marburg

News

• My joint work with Corinna Coupette and Bastian Rieck on hypergraph curvatures got accepted to ICLR. 2022/01.
• I became an Open-Science Ambassador. 2022/12
• I became a guest researcher in the department for Algorithms & Complexity at the Max Planck Institute for Informatics. 2022/10
• My work on efficiently factorizing boolean matrices using proximal gradient descent got accepted at NeurIPS, 2022.
• I presented a poster about Characterizing Cancer Types using Statistically Significant Gene Signatures at the Otto Warburg Summer School for Computational Cancer Research, 2022.
  
• My joint work with Corinna Coupette and Jilles Vreeken on differentially describing groups of graphs got accepted at AAAI, 2022.

Publications

• Corinna Coupette, Sebastian Dalleiger, and Bastian Rieck.
  Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework. ICLR, 2023.
  [preprint, OpenReview, A*]
• Sebastian Dalleiger, Jilles Vreeken
  Efficiently Factorizing Boolean Matrices using Proximal Gradient Descent. NeurIPS, 2022.
  [src, paper, bibtex, A*]
• Sebastian Dalleiger, Jilles Vreeken
  Discovering Significant Patterns under Sequential False Discovery Control. KDD, 2022.
  [src, paper, bibtex, A*]
• Corinna Coupette, Sebastian Dalleiger, and Jilles Vreeken
  Differentially Describing Groups of Graphs. AAAI, 2022.
  [src, paper, bibtex, A*]
• Sebastian Dalleiger and Jilles Vreeken
  The Relaxed Maximum Entropy Distribution and its Application to Pattern Discovery. ICDM, 2020.
  [src, paper, bibtex, A*]
• Sebastian Dalleiger and Jilles Vreeken
  Explainable Data Decompositions. AAAI, 2020.
  [src, paper, bibtex, A*]

Reviewing

AISTATS (2021) • DSAA (2019) • ECML PKDD (2020, '21) • ICDM (2018--19) • ICML (2018) • KAIS (2022) • KDD (2018--22) • NeurIPS (2020) • SDM (2018, '20)

Program Committee

CPAIOR (2016) • ECML PKDD (2021) • IDA (2022) • KDD (2023)