Domain Adaptation via Low-Rank Basis Approximation Christoph Raab 1 and Frank-Michael Schleif 2 1 University of applied Science W¨ urzburg-Schweinfurt, W¨ urzburg, Germany christoph.raab@fhws.de 2 The University of Birmingham, Edgbaston, Birmingham B15 2TT, United Kingdom schleify@cs.bham.ac.uk Abstract. Transfer learning focuses on the reuse of supervised learn- ing models in a new context. Prominent applications can be found in robotics, image processing or web mining. In these areas, learning sce- narios change by nature, but often remain related and motivate the reuse of existing supervised models. While the majority of symmetric and asymmetric domain adaptation algorithms utilize all available source and target domain data, we show that domain adaptation requires only a substantial smaller subset. This makes it more suitable for real-world scenarios where target domain data is rare. The presented approach finds a target subspace representation for source and target data to address domain differences by orthogonal basis transfer. We employ Nystr¨ om techniques and show the reliability of this approximation without a par- ticular landmark matrix by applying post-transfer normalization. It is evaluated on typical domain adaptation tasks with standard benchmark data. Keywords: Transfer Learning · Domain Adaptation · Nystr¨ om Approx- imation · Basis Transfer · Singular Value Decomposition 1 Introduction Supervised learning and particular classification, is an important task in machine learning with a broad range of applications. The obtained models are used to predict the labels of unseen test samples. In general, it is assumed that the underlying domain of interest is not changing between training and test samples. If the domain is changing from one task to a related but different task, one would like to reuse the available learning model. Domain differences are quite common in real-world scenarios and eventually lead to substantial performance drops [22]. A practical example is the classification of web pages: A classifier is trained in the domain of university web pages with a word distribution according to uni- versities and in the test scenario, the domain has changed to non-university web pages where the word distribution may not be similar to training distribution. arXiv:1907.01343v1 [cs.LG] 2 Jul 2019