GENERALIZATION BOUNDS FOR DOMAIN ADAPTATION VIA DOMAIN TRANSFORMATIONS

2018-09-20
Many domain adaptation methods are based on learning a projection or a transformation of the source and target domains to a common domain and training a classifier there, while the performance of such algorithms has not been theoretically studied yet. Previous studies proposing generalization bounds for domain adaptation relate the target loss to the discrepancy between the source and target distributions, however, do not take into account the possible effects of learning a transformation between the two domains. In this work, we present generalization bounds that study the target performance of domain adaptation methods learning a transformation of the source and target domains along with a hypothesis. We show that, under some conditions on the loss regularity, if the domain transformations reduce the distribution distance at a sufficiently high rate, then the expected target loss can be bounded with probability improving at an exponential rate with the number of labeled samples.
IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP)

Suggestions

Domain Adaptation with Nonparametric Projections
Vural, Elif (2019-08-22)
Domain adaptation algorithms focus on a setting where the training and test data are sampled from related but different distributions. Various domain adaptation methods aim to align the source and target domains in a new common domain by learning a transformation or projection. In this work, we learn a nonlinear and nonparametric projection of the source and target domains into a common domain along with a linear classifier in the new domain. Experiments on image data sets show that the proposed nonlinear a...
DOMAIN ADAPTATION VIA TRANSFERRING SPECTRAL PROPERTIES OF LABEL FUNCTIONS ON GRAPHS
Pilanci, Mehmet; Vural, Elif (2016-07-12)
We propose a domain adaptation algorithm that relies on a graph representation of data samples in the source and target domains. The algorithm combines the information of the known class labels in the source and target domains through the Fourier coefficients of the class label function in the two graphs. The proposed method does not require an ordering or a one-to-one mapping between the samples of the source and target domains; instead, it uses only a small set of matched pairs that serve the purpose of "...
User-guided transformations for ontology based simulation design
Özdikiş, Özer; Durak, Umut; Oğuztüzün, Mehmet Halit S. (null; 2009-12-01)
Using domain knowledge represented as ontologies for the design of domain specific architectures is a promising approach for better reusability. Tool support is essential for this approach to be effective. We present a flexible, user- guided transformation method to generate a framework architecture model from a domain model. The latter is in the form of an OWL ontology, and the former is in the form of a UML class diagram. We introduce a transformation tool that allows the user to configure mappings from t...
Domain Adaptation on Graphs via Frequency Analysis
Pilancı, Mehmet; Vural, Elif (2019-08-22)
Classical machine learning algorithms assume the training and test data to be sampled from the same distribution, while this assumption may be violated in practice. Domain adaptation methods aim to exploit the information available in a source domain in order to improve the performance of classification in a target domain. In this work, we focus on the problem of domain adaptation in graph settings. We consider a source graph with many labeled nodes and aim to estimate the class labels on a target graph wit...
Domain adaptation on graphs by learning aligned graph bases
Pilancı, Mehmet; Vural, Elif; Department of Electrical and Electronics Engineering (2018)
In this thesis, the domain adaptation problem is studied and a method for domain adaptation on graphs is proposed. Given sufficiently many observations of the label function on a source graph, we study the problem of transferring the label information from the source graph to a target graph for estimating the target label function. Our assumption about the relation between the two domains is that the frequency content of the label function, regarded as a graph signal, has similar characteristics over the so...
Citation Formats
E. Vural, “GENERALIZATION BOUNDS FOR DOMAIN ADAPTATION VIA DOMAIN TRANSFORMATIONS,” presented at the IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP), Aalborg, DENMARK, 2018, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/52582.