Transfer Learning for Evolving Domains
TrED formalizes transfer learning for domains whose data availability evolves over time, arguing classical settings are regimes along one trajectory, and remains unsolved.
The paper introduces Transfer Learning for Evolving Domains (TrED), formalizing transfer learning as a trajectory problem where target data and labels are progressively collected. TrED is specified by a data availability process fixed by the environment, a freely chosen learning protocol, and an evaluation criterion scoring the whole trajectory of models. Classical settings like domain generalization, domain adaptation, and multi-domain learning are recovered as regimes within this framework. The authors survey the literature and find most methods are tailored to a single regime, leaving TrED a well-posed open problem.
- Formalizes transfer learning as a trajectory over evolving data availability
- Classical settings become regimes within the unified TrED framework
- Existing methods optimize single regimes, not the whole trajectory
- Positioned as a well-posed, unsolved research direction
From the original article
1 min read at arxiv.orgTransfer learning explores how to leverage knowledge from various tasks or domains (sources) to enhance predictive performance in related tasks or domains (targets).
By Ricardo Ribeiro Pereira · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.