01414nam a2200169 a 4500 20260901030329.0 250101s2020 xx o 000 0 eng d Mohammad J. Hashemi General Domain Adaptation Through Proportional Progressive Pseudo Labeling arXiv 2020 text online resource Domain adaptation helps transfer the knowledge gained from a labeled source domain to an unlabeled target domain. During the past few years, different domain adaptation techniques have been published. One common flaw of these approaches is that while they might work well on one input type, such as images, their performance drops when applied to others, such as text or time-series. In this paper, we introduce Proportional Progressive Pseudo Labeling (PPPL), a simple, yet effective technique that can be implemented in a few lines of code to build a more general domain adaptation technique that can be applied on several different input types. At the beginning of the training phase, PPPL progressively reduces target domain classification error, by training the model directly with pseudo-labeled target domain samples, while excluding samples with more likely wrong pseudo-labels from the train Open access — freely available to read. https://arxiv.org/pdf/2012.13028v1 Read the full paper (PDF) ERES 643 643 0 0 0 3 CYB MAIN MAIN SCICOMP 2026-09-01 0 YGE000904 2026-09-01 03:03:30 https://arxiv.org/pdf/2012.13028v1 2026-09-01 PAPER