activity
20172021
most citedInterpreting Classifiers through Attribute Interactions in Datasets

31 citations · 31 across the 2 of their papers we have counts for

collaborators

5 papers

cs.CL2021

Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network

Janne Pylkkönen, Antti Ukkonen, Juho Kilpikoski +2

Adaption of end-to-end speech recognition systems to new tasks is known to be challenging. A number of solutions have been proposed which apply external language models with variou…

cs.DS2018

Randomisation Algorithms for Large Sparse Matrices

Kai Puolamäki, Andreas Henelius, Antti Ukkonen

In many domains it is necessary to generate surrogate networks, e.g., for hypothesis testing of different properties of a network. Furthermore, generating surrogate networks typica…

cs.SI2017

Large-scale study of social network structure and team performance in a multiplayer online game

Antti Ukkonen, Juho Hamari

A question of interest in both theory and practice is if and how familiarity between members of a team, expressed in terms of social network structure, relates to the success of th…

cs.DS2017

Crowdsourced correlation clustering with relative distance comparisons

Antti Ukkonen

Crowdsourced, or human computation based clustering algorithms usually rely on relative distance comparisons, as these are easier to elicit from human workers than absolute distanc…

stat.ML201731 cited

Interpreting Classifiers through Attribute Interactions in Datasets

Andreas Henelius, Kai Puolamäki, Antti Ukkonen

In this work we present the novel ASTRID method for investigating which attribute interactions classifiers exploit when making predictions. Attribute interactions in classification…