Xiaoran Yan, an assistant research scientist at the IU Network Science Institute, joined the team after serving as a postdoctoral research associate in the Information Sciences Institute at the University of Southern California.
Yan’s theoretical interests remain on mathematical theories and models of networks, focusing on community structures and dynamical processes on networks. Yan received his PhD in Computer Science from the University of New Mexico and spent time as a graduate fellow at the Santa Fe Institute.
Read on to find out how Yan homed in on data and why he values the interdisciplinary nature of IUNI.
Q: What does your research focus on?
Previously, I was a theoretically-focused computer scientist. So I’d design these elaborate algorithms and make proofs of how fast they are and how accurate they are and would pretend to run actual experiments with them. I’ve since found the real value lies in the data itself. Without data, you can make your theory-crafting as sophisticated as you want, but it won’t lead to real application that can be applied to the real world.
My research combines computer science, which focuses a lot on algorithm building, and basically finding machine-learning or AI-related techniques to apply to network data. But when you have to apply these algorithms to social systems or biological systems, for example, you have to at least be informed about what they’re trying to do. So that’s where the sense of collaboration started and I rendered myself to this interdisciplinary adventure.
Q: Were collaboration and interdisciplinary research factors in you joining IUNI?
I’m a computer scientist by training, but in my dissertation years, my advisor was trained as a physicist. I had statisticians and biologists on my dissertation committee, so I was exposed to this interdisciplinary way of thinking and doing research in the early stages of my career, and that’s the nature of network science. So the whole idea of an institute across disciplines and boundaries with so many different departments and schools joining forces — I haven’t seen anything like that before.
My other big draw for IUNI was they had these giant bibliographic datasets like the Web of Science. And at the end of my PhD, I was realizing more and more that I need to work with real data and the Web of Science is one of the best datasets you can get your hands on and get familiar with just by being part of the academia.
Q: What led you to get into informetrics?
I started being a bibliographic researcher after I came to IU. Informetrics is interesting to me because, as researchers, we are all part of it. Unlike biological networks or financial networks, which I’ve never been part of, I like working with scientometric data because the scholarly networks that help people publish are already embedded in our lives, so we feel directly associated with them.
Q: How has bibliographics spread into your projects?
I work a lot on CADRE (Collaborative Archive & Data Research Environment) and the more I deal with data, the more I realize how important data is — and just generally the lack of standards and lack of agreement in the bibliometrics field. To be truly reproducible and scientifically unbiased, you have to take into account how the data is collected, cleaned, modeled, all the way through to the end — and that’s the big picture for CADRE. With another project, Science Genome (YY Ahn, IUB Informatics), we are focusing on a graph-embedding algorithm. Embedding allows us to transform all the different information from bibliographic datasets into a common mathematical representation.
Q: What are some other projects you’re working on?
I work on a project with Liana (Apostolova, IUSM) where we are creating an algorithm that’s trying to figure out how a combination of factors contributes to the cognitive decline in Alzheimer’s disease. I’m also involved in a climate change project that Santo (Fortunato, IUB Informatics) has put together where we study climate change from a data science point-of-view. Another project I’ve been involved with for a long time is about brain networks, and I collaborated with Olaf (Sporns, IUB Psychological and Brain Sciences) on that.
Read some of Xiaoran’s recent publications:
- Efficient network navigation with partial information by X. Yan, O. Sporns, A. Avena-Koenigsberger
- The impact of air transport availability on research collaboration: A case study of four universities by A. Ploszaj, X. Yan, K. Börner
- Weight thresholding on complex networks by X. Yan, L. G. S. Jeub, A. Flammini, F. Radicchi, S. Fortunato
- Weighted Stochastic Block Models of the Human Connectome across the Life Span by J. Faskowitz, X. Yan, X. Zuo, O. Sporns
- Graph Filters and the Z-Laplacian by X. Yan, B. M. Sadler, R. J. Drost, P. L. Yu, K. Lerman