This paper starts from the observation that mobile and edge devices are powerful enough to execute Machine Learning (ML) application components, which in turn creates opportunities to keep privacy-sensitive data close to its source. Composing and deploying a distributed ML application is far from trivial because the optimal configuration depends on the application’s goals and execution context, both of which may change throughout its lifetime. Prior research on context-aware reconfigurations in ML based applications offer limited capabilities for dynamically migrating software components between mobile, edge and cloud devices. In this paper, we propose a context-aware middleware that enables automated optimizations of the application deployment in order to satisfy the application’s functional goals while the execution context changes in terms of available computation, memory and network resources. We use finite state machines to model the reconfiguration of the application based on contextual triggers and facilitate system design through the abstraction of system states. We illustrate the benefits of our approach with an image recognition application with well-defined performance goals that is deployed in a three-tier mobile-edge-cloud architecture.

Recommender systems have gained prominence in bringing users tailor-made content from the web aiding their decision making process. However, this personalization comes at a cost of privacy of sharing personal information with the recommendation provider. Moreover, with growing sizes of datasets and models, centralized processing of such data has become challenging. To this end, we propose a federated matrix factorization algorithm to enable personal data to be stored and used on-device for training while sending updates to train a centralized model. We illustrate preliminary results from our algorithm applied to recommendation of articles to users of a mobile application based on their reading history. We compare our performance with centralized matrix factorization applied on the same dataset.

Collaborative browsing, or co-browsing, is the co-navigation of the web with other people at-a-distance, supported by software that takes care of synchronizing the browsers. Current state-of-the-art solutions are able to do co-browsing of "static web pages", and do not support the synchronization of JavaScript interactions. However, currently many web pages use JavaScript and Ajax techniques to create highly dynamic and interactive web applications. In this paper, we describe two approaches for co-browsing that both support the synchronization of the JavaScript and Ajax interactions of dynamic web pages. One approach is based on synchronizing the output of the JavaScript engine by sending over the changes made on the DOM tree. The other approach is based on synchronizing the input of the JavaScript engine by synchronizing UI events and incoming data. Since the latter solution offers a better user experience and is more scalable, it is elaborated in more detail. An important aspect of both approaches is that they operate at the DOM level. Therefore, the client-side can be implemented in JavaScript and no browser extensions are required. To the best of the authors' knowledge this is the first DOM-level co-browsing solution that also enables co-browsing of the dynamic interaction parts of web pages. The presented co-browsing solution has been implemented in a research demonstrator which allows users to do co-browsing of web-applications on browser-based networked televisions.