Print Email Facebook Twitter Evaluating the Effectiveness of Importance Weighting Techniques in Mitigating Sample Selection Bias Title Evaluating the Effectiveness of Importance Weighting Techniques in Mitigating Sample Selection Bias Author TOCIU, Andrei (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor P. Gonçalves, Joana (mentor) Tepeli, Y.I. (mentor) Urbano, Julián (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2023-06-28 Abstract Importance weighting is a class of domain adaptation techniques for machine learning, which aims to correct the discrepancy in distribution between the train and test datasets, often caused by sample selection bias. In doing so, it frequently uses unlabeled data from the test set. However, this approach has certain drawbacks: it requires retraining for each new test set and fails when the number of test samples is very small. Therefore, we seek to study the performance of importance weighting techniques when the unlabeled data comes from an underlying domain, instead of one specific test set. We propose an evaluation framework inspired from scenarios traditionally known for posing difficulties to importance weighting and apply it to two popular algorithms, KMM and KLIEP. Our results reveal that both algorithms produce statistically significant classification improvements in most experiments. However, their performance is highly dependent on the characteristics of the dataset and the sampling bias. In particular, class overlap seems to influence adaptation ability in the case of unequal conditional probabilities of the source and target domains, while the "intensity" of the sampling bias is an important confounding factor when the train set size is small. Subject Sample Selection BiasDomain AdaptationImportance Weightingsampling bias To reference this document use: http://resolver.tudelft.nl/uuid:ae834964-aaf2-46cd-8dc2-b8b4cafabb71 Part of collection Student theses Document type bachelor thesis Rights © 2023 Andrei TOCIU Files PDF CSE3000_Final_Paper_Andre ... _final.pdf 14.19 MB Close viewer /islandora/object/uuid:ae834964-aaf2-46cd-8dc2-b8b4cafabb71/datastream/OBJ/view