TL;DR
This paper proposes a novel and efficient NTL approach using a dynamic Early-Exit Network, named ENL-DEE, which leverages Bayesian theory and dynamic neural networks to address limitations in non-transferable learning.
Deep neural networks excel in various tasks but struggle to generalize across evolving data distributions, leading to significant performance degradation under domain shifts. Domain incremental learning (DIL) addresses this challenge by enabling models to continuously adapt while retaining prior knowledge. Among existi...
Modern machine learning pipelines increasingly rely on reusing pretrained and foundation models across downstream tasks. These pretrained models can differ not only in performance but also in how they can be used: some only provide black-box predictions, while others may permit white-box access to internal representati...
Experimental results demonstrate that proposed Bayesian domain weighting method could achieve stable and efficient domain weights learning, and identifies optimal mixtures while consuming substantially less data than search-based function-fitting methods, revitalizing optimization-based domain weighting for large-scale...
This work introduces a novel measure, the relative parameter-importance, which measures the relative importance of each parameter with respect to both the current and past tasks, and allows the update of parameters with high past-task importance when they have low relative-importance, thus enabling backward knowledge t...
Domain generalization (DG) aims to learn predictive models from multiple source domains that maintain performance on unseen target domains. Distributionally robust optimization (DRO) addresses distribution shift by minimizing the worst-case risk over an uncertainty set of plausible test distributions. However, if this...
This work proposes Context-Constrained Transfer Learning via ANchoring and DIstillation (TL-ANDI), a posterior-aware distillation framework for TFMs that constructs a compact source context by solving a budget-constrained optimal transport problem whose cost jointly measures target covariate coverage and posterior comp...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
