Transfer learning for adapting to changing data over time

Transfer Learning for Evolving Domains

Machine Learning

Summary

Many computer programs learn to solve tasks using examples, but often the type and amount of data they get changes over time. The authors point out that most existing learning methods only handle fixed amounts of data at once, not gradually growing data from a new source. They propose a broader way to think about learning that captures how data evolves, calling this Transfer Learning for Evolving Domains (TrED). Their idea helps unify current approaches and highlights that making methods work well throughout changing data availability is still an open challenge.

What this means in practice

A position paper. It proposes an approach and reports no results.

Authors

Ricardo Ribeiro Pereira, Jacopo Bono, Hugo Ferreira, Pedro Ribeiro, Pedro Saleiro, Pedro Bizarro, Carlos Soares

Abstract

Transfer learning explores how to leverage knowledge from various tasks or domains (sources) to enhance predictive performance in related tasks or domains (targets). Typically, transfer learning research is segmented into several isolated sub-areas (such as domain generalisation, domain adaptation, or multi-domain learning), each making distinct assumptions about target data availability, namely how much data and how many labels are available at training time. However, in many real-world applications, data availability is not fixed but evolves over time, as instances and labels are progressively collected from a new domain. Each of the classical settings then describes only a snapshot of a trajectory that a deployed system must traverse in full. We formalise this trajectory as a transfer learning problem in its own right, Transfer Learning for Evolving Domains (TrED), specified by a data availability process fixed by the environment, a learning protocol that the method is free to choose, and an evaluation criterion that scores the whole trajectory of models rather than a single one. Within this formalism, the classical settings are recovered as regimes that a learner may pass through, rather than as separate problems that TrED concatenates. We then examine the transfer learning literature to identify mechanisms that are promising building blocks for a solution, and find that most methods are tailored to a single regime and that even the strongest existing candidates do not yet optimise the whole trajectory. We argue that TrED is a well-posed and unsolved problem, and an important direction for future research.