Decentralized machine learning tackles the problem of learning useful models when data is distributed among several clients. The most prevalent decentralized setting today is federated learning (FL), where a central server orchestrates the learning among clients. In this work, we contribute to the relatively understudied sub-field of generative modelling in the FL framework.We study the task of how to train generative adversarial networks (GANs) when training data is heterogeneously distributed (non-iid) over clients and cannot be shared. Our objective is to train a generator that is able to sample from the collective data distribution centrally, while the client data never leaves the clients and user privacy is respected. We show using standard benchmark image datasets that existing approaches fail in this setting, experiencing so-called client drift when the local number of epochs becomes to large and local parameters drift too far away in parameter space. To tackle this challenge, we propose a novel approach named EFFGAN: Ensembles of fine-tuned federated GANs. Being an ensemble of local expert generators, EFFGAN is able to learn the data distribution over all clients and mitigate client drift. It is able to train with a large number of local epochs, making it more communication efficient than previous works.

Great environmental problems are facing us at an unprecedented level.One way of approaching these global challenges is by transitioning from a linear economy to a circular one. In a circular economy, product and material flows become circular, which can significantly improve resource efficiency for environmental sustainability. This can help with minimizing waste and pollution and aid in the regeneration of nature.Meanwhile, transitioning from linear business models to circular business models (CBMs) often leads to a number of financial risks for product companies, since they need to secure more capital in a stock of products that will be rented out over time. This leads to a slower, more volatile cash flow in the short term compared to linear direct sales of products.In this work, we address this problem by reducing the uncertainty of the future value of products. This can increase the willingness among financiers to be part of the development of new circular business models (CBMs). In particular, we study the predictability of online auction end prices using machine learning. The models are trained and evaluated on data collected from a Swedish online auction site.Our results show that deep learning is able to model the residual value of second-hand items on the market using user-uploaded text and images. Our hypothesis is that this technique will be useful to estimate the value of second-hand inventories and to help estimate the value of circular businesses, aiding in a transition from a linear to a circular economy.

Data privacy is an increasingly important aspect of many real-world analytics tasks. Data sources that contain sensitive information may have immense potential which could be unlocked using the right privacy enhancing transformations, but current methods often fail to produce convincing output. Furthermore, finding the right balance between privacy and utility is often a tricky trade-off. In this work, we propose a novel approach for data privatization, which involves two steps: in the first step, it removes the sensitive information, and in the second step, it replaces this information with an independent random sample. Our method builds on adversarial representation learning which ensures strong privacy by training the model to fool an increasingly strong adversary. While previous methods only aim at obfuscating the sensitive information, we find that adding new random information in its place strengthens the provided privacy and provides better utility at any given level of privacy. The result is an approach that can provide stronger privatization on image data, and yet be preserving both the domain and the utility of the inputs, entirely independent of the downstream task.