Welcome to PEARC20! PEARC20’s theme is “Catch the Wave.” This year’s theme embodies the spirit of the community’s drive to stay on pace and in front of all the new waves in technology, analytics, and a globally connected and diverse workforce. We look forward to this year’s PEARC20 virtual meeting, where we can share scientific discovery and craft the future infrastructure.
The conference will be held in Pacific Time (PT) and the times listed below are in Pacific Time.
The connection information for all PEARC20 workshops, tutorials, plenaries, track presentations, BOFs, Posters, Visualization Showcase, and other affiliated events, are in the PEARC20 virtual conference platform, Brella. If you have issues joining Brella, please email pearcinfo@googlegroups.com.
🏆 Best Paper in “Trending now – machine learning and artificial intelligence” Track
Understanding highly-dimensional data sets is a complex task. Traditionally, this problem has been tackled with linear pipelines that rely on mathematical models and algorithms to summarize relationships and structure, producing a visual representation of the data in a collapsed, low-dimensional form. The main issue with these traditional pipelines is that they are driven solely by algorithms or models, and without a human in the loop, they can potentially limit sense-making by masking expected or known structure in the data. Textual data, such as that contained in research publications, is one example of unstructured highly dimensional data, wherein the raw data must be converted to an abstract numeric representation that is highly dimensional. In recent years, Semantic Interaction has become an interesting approach to enabling model steering in Visual Analytics systems, as it provides mechanisms with which to adjust the parameter space, explore data, and test hypotheses. In order to facilitate this interaction modality, Semantic Interaction systems need to invert the computation of one or more mathematical models to support a bidirectional structure within their pipelines. Most examples of Semantic Interaction systems are limited to linear models to allow for this bidirectionality. In this paper we propose an inexpensive neural encoder approach to performing backward and forward computations within semantic interaction pipelines for analyzing textual data. We show that this approach allows for the efficient "merging" of new instances into a previously trained model without retraining. It also provides a reverse link, allowing the parameters of a trained model to be affected by user interactions with the visual representation of data. To demonstrate the usefulness of this approach we present the Zexplorer system, a tool for exploring Large Document Collections of Research papers with Semantic Interaction. The Zexplorer system is built as an extension to Zotero, a widely used open source bibliography system.
