PVeRA extends VeRA by making its frozen random low-rank matrices probabilistic, enabling better handling of ambiguities and outperforming prior adapters on the VTAB-1k benchmark.
Learning multiple layers of features from tiny images
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
FedQUIT performs on-device unlearning in federated learning by distilling from a virtual teacher that penalizes true-class confidence on forget data while preserving other output relationships, matching or exceeding prior methods with lower overhead than retraining.
citing papers explorer
-
PVeRA: Probabilistic Vector-Based Random Matrix Adaptation
PVeRA extends VeRA by making its frozen random low-rank matrices probabilistic, enabling better handling of ambiguities and outperforming prior adapters on the VTAB-1k benchmark.
-
FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher
FedQUIT performs on-device unlearning in federated learning by distilling from a virtual teacher that penalizes true-class confidence on forget data while preserving other output relationships, matching or exceeding prior methods with lower overhead than retraining.