Breaking the Reclustering Barrier in Centroid-based Deep Clustering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929737316696064 |
|---|---|
| author | Miklautz, Lukas Klein, Timo Sidak, Kevin Leiber, Collin Lang, Thomas Shkabrii, Andrii Tschiatschek, Sebastian Plant, Claudia |
| author_facet | Miklautz, Lukas Klein, Timo Sidak, Kevin Leiber, Collin Lang, Thomas Shkabrii, Andrii Tschiatschek, Sebastian Plant, Claudia |
| contents | This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains. Practitioners commonly address early saturation with periodic reclustering, which we demonstrate to be insufficient to address performance plateaus. We call this phenomenon the "reclustering barrier" and empirically show when the reclustering barrier occurs, what its underlying mechanisms are, and how it is possible to Break the Reclustering Barrier with our algorithm BRB. BRB avoids early over-commitment to initial clusterings and enables continuous adaptation to reinitialized clustering targets while remaining conceptually simple. Applying our algorithm to widely-used centroid-based DC algorithms, we show that (1) BRB consistently improves performance across a wide range of clustering benchmarks, (2) BRB enables training from scratch, and (3) BRB performs competitively against state-of-the-art DC algorithms when combined with a contrastive loss. We release our code and pre-trained models at https://github.com/Probabilistic-and-Interactive-ML/breaking-the-reclustering-barrier . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_02275 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Breaking the Reclustering Barrier in Centroid-based Deep Clustering Miklautz, Lukas Klein, Timo Sidak, Kevin Leiber, Collin Lang, Thomas Shkabrii, Andrii Tschiatschek, Sebastian Plant, Claudia Machine Learning Artificial Intelligence This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains. Practitioners commonly address early saturation with periodic reclustering, which we demonstrate to be insufficient to address performance plateaus. We call this phenomenon the "reclustering barrier" and empirically show when the reclustering barrier occurs, what its underlying mechanisms are, and how it is possible to Break the Reclustering Barrier with our algorithm BRB. BRB avoids early over-commitment to initial clusterings and enables continuous adaptation to reinitialized clustering targets while remaining conceptually simple. Applying our algorithm to widely-used centroid-based DC algorithms, we show that (1) BRB consistently improves performance across a wide range of clustering benchmarks, (2) BRB enables training from scratch, and (3) BRB performs competitively against state-of-the-art DC algorithms when combined with a contrastive loss. We release our code and pre-trained models at https://github.com/Probabilistic-and-Interactive-ML/breaking-the-reclustering-barrier . |
| title | Breaking the Reclustering Barrier in Centroid-based Deep Clustering |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2411.02275 |