pith. sign in

Up to 100x faster data-free knowledge distillation

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2023 1

verdicts

UNVERDICTED 1

representative citing papers

Task-Distributionally Robust Data-Free Meta-Learning

cs.LG · 2023-11-23 · unverdicted · novelty 5.0

The paper proposes a trustworthy DFML framework that mitigates task-distribution shift and corruption via synthetic task reconstruction, historical task replay through interpolation, and automatic filtering of untrustworthy models.

citing papers explorer

Showing 1 of 1 citing paper.

  • Task-Distributionally Robust Data-Free Meta-Learning cs.LG · 2023-11-23 · unverdicted · none · ref 8

    The paper proposes a trustworthy DFML framework that mitigates task-distribution shift and corruption via synthetic task reconstruction, historical task replay through interpolation, and automatic filtering of untrustworthy models.