Details (Don't) Matter: Isolating Cluster Information in Deep Embedded Spaces

Authors: Lukas Miklautz, Lena G. M. Bauer, Dominik Mautz, Sebastian Tschiatschek, Christian Böhm, Claudia Plant

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate all algorithms with six different data sets focusing on common DC benchmarks like MNIST [Le Cun et al., 1998], Fashion-MNIST [Xiao et al., 2017] and USPS. Additionally, we use a data set based on real world images of traffic signs (GTSRB) [Houben et al., 2013], recorded under different camera angles and daylight conditions, and two synthetic data sets to show the impact of irrelevant information on DC performance.
Researcher Affiliation Academia 1Faculty of Computer Science, University of Vienna, Vienna, Austria 2Ludwig-Maximilians-Universit at M unchen, Munich, Germany 3ds:Uni Vie, Austria, 4MCML, Germany
Pseudocode No No explicit pseudocode or algorithm blocks were found.
Open Source Code Yes We uploaded our code and supplement at https://gitlab.cs.univie.ac.at/lukas/acedec public.
Open Datasets Yes We evaluate all algorithms with six different data sets focusing on common DC benchmarks like MNIST [Le Cun et al., 1998], Fashion-MNIST [Xiao et al., 2017] and USPS. Additionally, we use a data set based on real world images of traffic signs (GTSRB) [Houben et al., 2013], recorded under different camera angles and daylight conditions, and two synthetic data sets to show the impact of irrelevant information on DC performance.
Dataset Splits No The paper refers to "MNIST-Full" and "MNIST-Test" in Table 1, implying standard splits, but does not explicitly provide specific details on the train/validation/test dataset splits (percentages, sample counts, or methodology) within the main body of the paper. It refers to the supplementary material for further details: "Further explanations about the experiments, data sets, information on our hardware setup, compared methods, and all additional experiments are in the SP (Sec. 2)."
Hardware Specification No Further explanations about the experiments, data sets, information on our hardware setup, compared methods, and all additional experiments are in the SP (Sec. 2).
Software Dependencies No The paper refers to supplementary material for 'training budget, learning rate, optimizer, etc., see the SP (Sec. 2.4) for details)' but does not explicitly list specific software dependencies with version numbers in the main text.
Experiment Setup No We used the same settings for the training of all DC methods (training budget, learning rate, optimizer, etc., see the SP (Sec. 2.4) for details).