Networks are all around us. As such, network science is crucial for our understanding of many applications of high societal relevance (e.g., social and technological networks, epidemics, biological networks). Our research focuses on developing new machine learning methods to discover complex interactions and collective behaviors that determine how various types of events and behaviors in social networks are generated and propagated. In particular, we are interested in developing new approaches for social sensing that are relevant to the immediate concerns around pandemic detection and mitigation.
Selected Publications
K-hop learning: a network-based feature extraction for improved river flow prediction Proceedings Article
In: Proceedings of the 3rd International Workshop on Cyber-Physical Systems for Smart Water Networks, pp. 15–18, 2017.
From ideas to social signals: Spatiotemporal analysis of social media dynamics Proceedings Article
In: Proceedings of the 2nd International Workshop on Social Sensing, pp. 29–34, 2017.
Non-Stationary Bayesian Learning for Global Sustainability Journal Article
In: IEEE Transactions on Sustainable Computing, vol. 2, no. 3, pp. 304–316, 2017.
Multi-fractal characterization of bacterial swimming dynamics: a case study on real and simulated serratia marcescens Journal Article
In: Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 473, no. 2203, pp. 20170154, 2017.
Inferring microbial interactions from metagenomic time-series using prior biological knowledge Proceedings Article
In: Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, pp. 168–177, 2017.
Molecular communication with DNA cellular storage system Proceedings Article
In: Proceedings of the 4th ACM International Conference on Nanoscale Computing and Communication, pp. 1–6, 2017.
Our ‘Unlearning’ Research for GenAI Featured in The Daily Texan Post
Excited to see our collaborative research with JPMorgan Chase on an AI unlearning algorithm spotlighted in The Daily Texan! Check out the article at OpenReview.
Key Points
Epidemics
Viral outbreaks spread throughout networks of people via transmission events. We aim to combine human mobility data, network science, and machine learning to inform and mitigate the disease dynamics for COVID-19. Furthermore, we aim to build an always-on social sensing system to improve a population’s resilience to a novel virus.
Social Networks
Objective social media exhibit rich yet distinct temporal dynamics which cover a wide range of different scales. We are able to identify the compositional structures that can accurately characterize the complex social dynamics from these two social media. We further show that identifying these patterns can enable new applications such as anomaly detection and improved social dynamics forecasting. We aim to uncover new insights on understanding and engineering social media dynamics and their consequences on offline behaviors.
Biological Networks
It is well established that bacteria engage in social behavior and form networked communities via molecular signaling. We analyze the network dynamics and biofilm metrics, showing that our method can effectively reveal the underlying intercellular communication process and community organization within the biofilm. We claim that the application of social and network sciences to understanding bacteria population dynamics can aid in developing better drugs to control the many pathogenic bacteria that use social interactions to cause infections.