Now showing items 1-4 of 4

    • Algorithms for Approximate Subtropical Matrix Factorization 

      Karaev, Sanjar; Miettinen, Pauli (Springer Nature, 2018)
      Matrix factorization methods are important tools in data mining and analysis. They can be used for many tasks, ranging from dimensionality reduction to visualization. In this paper we concentrate on the use of matrix ...
      Tieteelliset aikakauslehtiartikkelit

    • Serenade: An Approach for Differentially Private Greedy Redescription Mining 

      Karjalainen, Maiju; Galbrun, Esther; Miettinen, Pauli (CEUR-WS Team, Redaktion Sun SITE, Informatik V, RWTH Aachen, Germany, 2023)
      We present an approach for mining differentially private redescriptions. Applying differential privacy to pattern mining approaches such as redescription mining is less straightforward than with numerical methods, in part ...

    • Stability and dynamics of communities on online question-answer sites 

      Metzler, Saskia; Günnemann, Stephan; Miettinen, Pauli (Elsevier BV, 2019)
      Social networks are present in our everyday lives, not just in face to face communication, but also when we communicate through the Internet. The latter leaves massive traces of data and thereby opens opportunities to ...
      Tieteelliset aikakauslehtiartikkelit

    • Visualizing Overlapping Biclusterings and Boolean Matrix Factorizations 

      Marette, Thibault; Miettinen, Pauli; Neumann, Stefan (Springer Nature Switzerland AG, 2023)
      Finding (bi-)clusters in bipartite graphs is a popular data analysis approach. Analysts typically want to visualize the clusters, which is simple as long as the clusters are disjoint. However, many modern algorithms find ...