09.08.2022
MCML Researchers With One Paper at KDD 2022
28th ACM SIGKDD International Conference on Knowledge Discovery and Data (KDD 2022). Washington, DC, USA, 14.08.2022–18.08.2022
We are happy to announce that MCML researchers are represented with one paper at KDD 2022. Congrats to our researchers!
Main Track (1 papers)
The DipEncoder: Enforcing Multimodality in Autoencoders.
KDD 2022 - 28th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Washington, DC, USA, Aug 14-18, 2022. DOI
Abstract
Hartigan’s Dip-test of unimodality gained increasing interest in unsupervised learning over the past few years. It is free from complex parameterization and does not require a distribution assumed a priori. A useful property is that the resulting Dip-values can be derived to find a projection axis that identifies multimodal structures in the data set. In this paper, we show how to apply the gradient not only with respect to the projection axis but also with respect to the data to improve the cluster structure. By tightly coupling the Dip-test with an autoencoder, we obtain an embedding that clearly separates all clusters in the data set. This method, called DipEncoder, is the basis of a novel deep clustering algorithm. Extensive experiments show that the DipEncoder is highly competitive to state-of-the-art methods.
MCML Authors
09.08.2022
Related
22.07.2025
Eyke Hüllermeier to Lead New DFG-Funded Research Training Group METEOR
MCML PI Eyke Hüllermeier to lead new DFG-funded RTG METEOR, uniting ML and control theory to build robust, explainable AI systems.
16.07.2025
AI-Powered Cortical Mapping for Neurodegenerative Disease Diagnoses - With Christian Wachinger
Research film with Christian Wachinger shows how AI maps the brain’s cortex to support diagnoses of neurodegenerative diseases.
©TUM
15.07.2025
ERC Proof of Concept Grants for Fabian Theis
Fabian Theis receives ERC Proof of Concept Grants for his project on deep learning methods for dynamic single-cell data analysis.
10.07.2025
Beyond Prediction: How Causal AI Enables Better Decision-Making - With Stefan Feuerriegel
Stefan Feuerriegel in our new film shows how Causal AI helps pick better actions by predicting outcomes for each possible decision.
