DDCL-Attention introduces a collapse-free prototype readout for transformers that decomposes the training loss exactly into reconstruction and diversity terms while providing stability guarantees via singular perturbation theory.
An overview on deep clustering.Neurocom- puting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Collapse-Free Prototype Readout Layer for Transformer Encoders
DDCL-Attention introduces a collapse-free prototype readout for transformers that decomposes the training loss exactly into reconstruction and diversity terms while providing stability guarantees via singular perturbation theory.