Machine Learning

, Volume 82, Issue 2, pp 123–155

Multi-way set enumeration in weight tensors

  • Elisabeth Georgii
  • Koji Tsuda
  • Bernhard Schölkopf
Open Access

DOI: 10.1007/s10994-010-5210-y

Cite this article as:
Georgii, E., Tsuda, K. & Schölkopf, B. Mach Learn (2011) 82: 123. doi:10.1007/s10994-010-5210-y


The analysis of n-ary relations receives attention in many different fields, for instance biology, web mining, and social studies. In the basic setting, there are n sets of instances, and each observation associates n instances, one from each set. A common approach to explore these n-way data is the search for n-set patterns, the n-way equivalent of itemsets. More precisely, an n-set pattern consists of specific subsets of the n instance sets such that all possible associations between the corresponding instances are observed in the data. In contrast, traditional itemset mining approaches consider only two-way data, namely items versus transactions. The n-set patterns provide a higher-level view of the data, revealing associative relationships between groups of instances. Here, we generalize this approach in two respects. First, we tolerate missing observations to a certain degree, that means we are also interested in n-sets where most (although not all) of the possible associations have been recorded in the data. Second, we take association weights into account. In fact, we propose a method to enumerate all n-sets that satisfy a minimum threshold with respect to the average association weight. Technically, we solve the enumeration task using a reverse search strategy, which allows for effective pruning of the search space. In addition, our algorithm provides a ranking of the solutions and can consider further constraints. We show experimental results on artificial and real-world datasets from different domains.


Tensor Multi-way set Dense pattern enumeration Quasi-hyper-clique N-ary relation Graph mining 

Copyright information

© The Author(s) 2010

Authors and Affiliations

  • Elisabeth Georgii
    • 1
    • 2
    • 3
  • Koji Tsuda
    • 4
    • 5
  • Bernhard Schölkopf
    • 6
  1. 1.Department of Empirical InferenceMax Planck Institute for Biological CyberneticsTübingenGermany
  2. 2.Friedrich Miescher Laboratory of the Max Planck SocietyTübingenGermany
  3. 3.Department of Information and Computer Science, Helsinki Institute for Information Technology, HIITAalto University School of Science and TechnologyAaltoFinland
  4. 4.Computational Biology Research CenterNational Institute of Advanced Industrial Science and Technology, AISTTokyoJapan
  5. 5.ERATO Minato ProjectJapan Science and Technology AgencyTokyoJapan
  6. 6.Department of Empirical InferenceMax Planck Institute for Biological CyberneticsTübingenGermany

Personalised recommendations