Projects per year
We study the impact of different pruning techniques on the representation learned by deep neural networks trained with contrastive loss functions. Our work finds that at high sparsity levels, contrastive learning results in a higher number of misclassified examples relative to models trained with traditional cross-entropy loss. To understand this pronounced difference, we use metrics such as the number of PIEs (Hooker et al., 2019), Q-Score (Kalibhat et al., 2022), and PD-Score (Baldock et al., 2021) to measure the impact of pruning on the learned representation quality. Our analysis suggests the schedule of the pruning method implementation matters. We find that the negative impact of sparsity on the quality of the learned representation is the highest when pruning is introduced early on in the training phase.
|Number of pages||10|
|Publication status||Published - 1 Jul 2022|
FingerprintDive into the research topics of 'Studying the impact of magnitude pruning on contrastive learning methods'. Together they form a unique fingerprint.
- 1 Active
FWF - DENISE - Doctoral School for Dependable Electronic-Based Systems
Mütze, A., Saukh, O., Römer, K. U. & Boano, C. A.
1/05/22 → 30/04/26
Project: Research project