Papers › ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale

ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale

2 Oct 2023arXiv:2310.01217archive 2025-07-28

Markus Frohmann, Carolin Holtermann, Shahed Masoudian, Anne Lauscher, Navid Rekabsaz

Multi-task learning (MTL) has shown considerable practical benefits, particularly when using language models (LMs). While this is commonly achieved by learning n tasks under a joint optimization procedure, some methods, such as AdapterFusion, divide the problem into two stages: (i) task learning, where knowledge specific to a task is encapsulated within sets of parameters (e.g., adapters), and (ii) transfer, where this already learned knowledge is leveraged for a target task. This separation of concerns provides numerous benefits (e.g., promoting reusability). However, current two-stage MTL introduces a substantial number of additional parameters. We address this issue by leveraging the usefulness of linearly scaling the output representations of source adapters for transfer learning. 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 transfer to a target task. Our experiments on three benchmarks (GLUE, SuperGLUE, and HumSet) and two encoder LMs show that ScaLearn consistently outperforms strong baselines with a small number of transfer parameters (~ $0.35$% of those of AdapterFusion). Remarkably, we observe that ScaLearn maintains its strong abilities even when further reducing parameters, achieving competitive results with only $8$ transfer parameters per target task. Our proposed approach thus demonstrates the power of simple scaling as a promise for more efficient task transfer.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

cpjku/scalearn officialmentioned in papermentioned on GitHubjaxMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Task LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FLIP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections