Skip to main content

Online collaboration has been popular for a while now, thanks to tools such as Dropbox and GitHub, but it took on new significance during the COVID-19 pandemic. Over the past year, more and more teams with members from multiple disciplines with different backgrounds have been collaborating and analyzing data online. This is where the research of Computer Science Professor Chen Li of UCI’s Donald Bren School of Information and Computer Sciences (ICS) comes into play. Li is working to develop new techniques that support novel online services for collaborative data analytics.

Working with Assistant Professor of Public Health Suellen Hopfer at UCI and Computer Science Professor Wei Wang of UCLA, Li is exploring how to support online analytics centered on machine learning. The three-year research project, Collaborative Machine-Learning-Centric Data Analytics at Scale, recently received $1.2 million in funding from the National Science Foundation (NSF). It builds on the Texera system currently used in several collaborative projects in Public Health at UCI.

The goal is to support collaborative data analytics with online services that

  • can be used by people without a strong IT background;
  • support ML-based operations including labeling, training, and classification;
  • support asynchronous collaboration; and
  • are scalable for big data analytics.

By meeting these requirements, the services would support both intradisciplinary and interdisciplinary teams across differing working schedules. Furthermore, the researchers are working to make state-of-the-art ML techniques more easily accessible as pre-packaged operators available in cloud-based services.

“The techniques will significantly lower the barriers to entry in terms of enabling domain-specific analysts — as opposed to computer-science-trained Big Data experts — to gather and to efficiently, effectively, and interactively analyze large quantities of data in different domains,” explain the researchers in their grant abstract. “Enabling and streamlining such analyses by domain scientists, ML experts, and systems developers stands to provide critical insights for use in areas such as public health, pandemic control, and government policies.”

— Shani Murray