1 code implementation • 23 Jan 2024 • Carolin Holtermann, Markus Frohmann, Navid Rekabsaz, Anne Lauscher
The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks.
1 code implementation • 2 Oct 2023 • Markus Frohmann, Carolin Holtermann, Shahed Masoudian, Anne Lauscher, Navid Rekabsaz
We introduce ScaLearn, a simple and highly parameter-efficient two-stage MTL method that capitalizes on the knowledge of the source tasks by learning a minimal set of scaling parameters that enable effective knowledge transfer to a target task.