MétaCan
← all works

A theory of learning from different domains

2009· article· en· 3,486 citations· W2104094955 on OpenAlex· 10.1007/s10994-009-5152-4

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian affiliationAn author listed a Canadian institution. This is the only route the usual frame has.

Abstract

Discriminative learning methods for classification perform well when training and test data are drawn from the same distribution. Often, however, we have plentiful labeled training data from a source domain but wish to learn a classifier which performs well on a target domain with a different distribution and little or no labeled training data. In this work we investigate two questions. First, under what conditions can a classifier trained from source data be expected to perform well on target data? Second, given a small amount of labeled target data, how should we combine it during training with the large amount of labeled source data to achieve the lowest target error at test time? We address the first question by bounding a classifier’s target error in terms of its source error and the divergence between the two domains. We give a classifier-induced divergence measure that can be estimated from finite, unlabeled samples from the domains. Under the assumption that there exists some hypothesis that performs well in both domains, we show that this quantity together with the empirical source error characterize the target error of a source-trained classifier. We answer the second question by bounding the target error of a model which minimizes a convex combination of the empirical source and target errors. Previous theoretical work has considered minimizing just the source error, just the target error, or weighting instances from the two domains equally. We show how to choose the optimal combination of source and target error as a function of the divergence, the sample sizes of both domains, and the complexity of the hypothesis class. The resulting bound generalizes the previously studied cases and is always at least as tight as a bound which considers minimizing only the target error or an equal weighting of source and target errors.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

The record

Venue
Machine Learning
Topic
Domain Adaptation and Few-Shot Learning
Field
Computer Science
Canadian institutions
University of Waterloo
Funders
Advanced Research Projects AgencyDefense Advanced Research Projects AgencyUniversity of PennsylvaniaNational Science Foundation
Keywords
Classifier (UML)Computer scienceWeightingDiscriminative modelArtificial intelligenceBounding overwatchPattern recognition (psychology)Bayes error rateLabeled dataMachine learningTest dataQuadratic classifierDivergence (linguistics)AlgorithmBayes classifierSupport vector machineNaive Bayes classifier
Has abstract in OpenAlex
yes