REVIEW 2 cited by
Hydra: Preserving Ensemble Diversity for Model Distillation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory. Therefore, recent research has focused on distilling ensembles into a single compact model, reducing the computational and memory burden of the ensemble while trying to preserve its predictive behavior. Most existing distillation formulations summarize the ensemble by capturing its average predictions. As a result, the diversity of the ensemble predictions, stemming from each member, is lost. Thus, the distilled model cannot provide a measure of uncertainty comparable to that of the original ensemble. To retain more faithfully the diversity of the ensemble, we propose a distillation method based on a single multi-headed neural network, which we refer to as Hydra. The shared body network learns a joint feature representation that enables each head to capture the predictive behavior of each ensemble member. We demonstrate that with a slight increase in parameter count, Hydra improves distillation performance on classification and regression settings while capturing the uncertainty behavior of the original ensemble over both in-domain and out-of-distribution tasks.
Forward citations
Cited by 2 Pith papers
-
Generative Data Mining with Longtail-Guided Diffusion
A diffusion model guided by a classifier's uncertainty signal generates hard but in-distribution images, and fine-tuning on them improves accuracy, especially on rare classes.
-
Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles
A repulsive last-layer ensemble trained with function-space diversity on OOD or augmented samples gives competitive uncertainty estimates at a fraction of deep-ensemble cost.
Discussion (0). Continue with ORCID to comment.