The Sanghani Center is home to high-profile research, garnering recognition within and beyond the data analytics community.
Our talented team has been recognized with many competitive research awards and featured in major news and media outlets such as the Wall Street Journal, Newsweek, the Boston Globe and the Chronicle of Higher Education.
A strong emphasis on research, a robust commitment to sustainability, and a large international presence among its faculty served as common themes in Virginia Tech’s showing in various national and global rankings this fall.
Following are the Sanghani Center’s 2022 summer and fall graduates:
Nikhil Muralidhar, advised by Naren Ramakrishnan and Anuj Karpatne, has earned a Ph.D. in computer science. His research interest is in leveraging machine learning to address problems in scientific applications leveraging data and scientific theory. He also received a graduate certificate in Urban Computing. The title of his dissertation is “Science Guided Machine Learning: Incorporating Scientific Domain Knowledge for Learning Under Data Paucity and Noisy Contexts.” In Fall 2022, Muralidhar joined the Computer Science Department at Stevens Institute of Technology in Hoboken, New Jersey, as an assistant professor and leads the Scientific Artificial Intelligence (ScAI) Lab to develop scientific machine learning solutions incorporating data and domain knowledge in physics, fluid dynamics, cyber-physical systems and disease modeling.
Xinyue Wang, advised by Edward Fox, has earned a Ph.D. in computer science. His research focuses on web archive processing and analysis infrastructure through distributed computation. The title of his dissertation is “Large Web Archive Collection Infrastructure and Services.” Wang is joining Yahoo in San Jose, California, as a research scientist.
Huiman Han, advised by Chris North, has earned a master’s degree in computer science. Her research focuses on visual analytics, interactive machine learning, and explainable artificial intelligence. The title of her thesis is “Explainable Interactive Projections for Image Data.” Huimin is joining LinkedIn in Mountain View, California, as a software engineer in Machine Learning.
Sarah Maxseiner, advised by Lynn Abbott, received a master’s degree in electrical and computer engineering. Her thesis is on assessing the quality level of hand-drawn sketches.
A team of four graduate students at the Sanghani Center for Artificial Intelligence and Data Analytics is one of nine international university teams selected to compete in the Alexa Prize SocialBot Grand Challenge 5 sponsored by Amazon.com Services LLC. Each participating team will receive up to a $250,000 research grant to build a skill that can help Alexa converse with users on popular topics and current events for at least 20 minutes while achieving a user rating of at least 4.0/5.0. Top finishing teams will also be eligible for various prizes. Read more here.
Funded by Amazon, housed in the College of Engineering, and directed by researchers at the Sanghani Center for Artificial Intelligence and Data Analytics on Virginia Tech’s campus in Blacksburg and at the Innovation Campus in Alexandria, the initiative was launched in March to support student and faculty-led development and implementation of innovative approaches to robust machine learning — such as ensuring that algorithms and models are resistant to errors and adversaries — that could address worldwide industry-focused problems. Read more here.
Having earned a bachelor of science degree in computer science at Virginia Tech in 2020, Han Liu remained at the university to continue his education and pursue a master’s degree.
“On a personal note, I love the beautiful surroundings in Blacksburg,” said Liu. “But more importantly, my decision was influenced by the professors I have met here who are passionate about their fields and actively support students in their studies and research.”
Liu, who is advised by Chris North, added that “as a graduate student, the Sanghani Center has provided me with many exciting academic and research opportunities.”
Liu’s research focuses on visual analytics and how to represent data in a way that helps users understand and interpret it more easily.
“Existing notebook platforms have different capabilities for supporting the use of visual analytics and it is not clear which platform to choose for implementing visual analytics notebooks,” said Liu. “My work explores how to best implement these notebooks to solve problems, particularly in data science scenarios.”
Her research at the Sanghani Center has focused on how students use the interactive dimensionality reduction application Andromeda. “I want to understand how students — when given complex data analysis tools — learn from the experience of conducting exploratory data analysis,” said Taylor, who is advised by Chris North.
For this study, the classroom teacher uploaded data describing projects to Andromeda with each point in the visualization representing a student’s design. With Andromeda controlled by the teacher, students used it to visualize, analyze, and compare their designs in extended conversation with each other and the teacher and collectively explore their design-related data.
““Despite not having the mathematical background to understand dimensionality reduction, the students in our study learned about relations between variables and felt that Andromeda helped them compare their designs in a friendly, but competitive manner,” Taylor said.
In the study, she said, the team also suggested ways of improving Andromeda’s utility as a public, educational resource and provided an example of class activity aligned with Virginia’s proposed Standards of Learning in data science.
Taylor was introduced to research in visualization while doing an undergraduate capstone project in human-computer interaction.
“The Sanghani Center conducts interesting research within data science and machine learning,” said Taylor, “and as a master’s degree student, it has afforded me useful connections across the field which will continue to be valuable as I will be remaining in the Blacksburg area as a machine learning engineer after graduation.”
Graduate students at the Sanghani Center often embark on summer internships to gain real-world experience and in some instances, enable them to also advance their own research interests and projects. Summer 2022 is no exception. While some companies and research labs are continuing to operate remotely, a number of students have returned to working on-site.
Following is a list of Sanghani Center interns, where they are working, and what they are doing:
Sikiru Adewale, a Ph.D. student in computer science, is a graduate technical research intern at Intel Corporation, working remotely. He is using machine learning to analyze the workloads dataset. His advisor is Ismini Lourentzou.
Jie Bu, a Ph.D student in computer science, is a machine learning research intern for an Apple Maps Team in Cupertino, California, working on-site. He is helping to optimize user experience and map services using deep learning methods. His advisor is Anuj Karpatne.
Satvik Chekuri, a Ph.D. student in computer science, is an natural language processing intern with the Deloitte Audit and Assurance Data Science team in New York City, working remotely on the entity extraction and entity linking problem for unstructured data in the financial domain. His advisor is Edward Fox.
Nurendra Choudhary, a Ph.D. student in computer science, is an applied science intern at Amazon A9 in Palo Alto, California, working on-site on use case of graph and language representation in the context of e-commerce platforms. His advisor is Chandan Reddy.
Elizabeth Christman, a master’s degree student in computer science, is a software engineering intern at Splunk in Blacksburg, Virginia, working remotely on automating the build process for Stream, a Splunk add-on for deep packet inspection. Her advisor is Chris North.
Arka Daw, a Ph.D. student in computer science, is a research intern at IBM T.J. Watson Research Center in New York, working on-site. He is developing physics-informed AI methods to solve inverse problems involving partial differential equations. His advisor is Anuj Karpatne.
Mohannad Elhamod, a Ph.D student in computer science, is an intern at NASA Langley Research Center in Hampton, Virginia, working remotely on applying machine learning in material engineering. His advisor is Anuj Karpatne.
Jiaying Gong, a Ph.D. student in computer science, is a research scientist intern at Rakuten in Boston, Massachusetts, working remotely on multi-label few-shot learning in natural language processing. Her advisor is Hoda Eldardiry.
Naveen Gupta, a master’s degree student in computer science, is a software engineering intern at Kentik in San Francisco, California, working remotely in the web development domain and using React, Node JS, and Express JS in building SAAS products. His advisor is Anuj Karpatne.
Huimin Han, a master’s degree student in computer science, is a machine learning engineer intern at LinkedIn in Sunnyvale, California, working on-site. She is exploring machine learning techniques to build the most accurate occupational taxonomy for every Linkedin member. Her advisor is Chris North.
Jianfeng He, a Ph.D. student in computer science, is an applied scientist intern on the AWS AI team at Amazon in Seattle, Washington, working on-site. He is doing research related to audio, text, and semantic understanding. His advisor is Chang-Tien Lu.
Meghana Holla, a master’s degree student in computer science, is a machine learning intern on the Data Technologies team at Bloomberg LP in New York, working on-site. She is researching and optimizing entity extraction methodologies on financial documents with emphasis on low inference times. Her advisor is Ismini Lourentzou.
Aneesh Jain, a master’s degree student in computer science, is a machine learning engineering intern at Cadence Solutions, working remotely on applications of language models in the healthcare domain. His advisor is Chandan Reddy.
Gaurang Karwande, a master’s degree student in the Bradley Department of Electrical and Computer Engineering, is a machine learning intern at VideaHealth, Inc., in Boston, Massachusetts, working on-site in the field of medical imaging and developing AI-powered solutions in dentistry. His advisor is Ismini Lourentzou.
Yoonjin Kim, a Ph. D. student in computer science, is a graduate software research intern at Intel IP and Competitive Analysis in Santa Clara, California, working an on-site/virtual hybrid. She is gaining industry exposure to the latest trend in workloads and workload-related research. Her advisor is Lenwood Heath.
M. Maruf, a Ph.D. student in computer science, is an applied scientist intern at Amazon.com in Seattle, Washington, working on-site to solve an image referencing problem with a goal of improving Amazon delivery experiences. His advisor is Anuj Karpatne.
Amarachi Blessing Mbakwe, a Ph.D. student in computer science, is an AI research associate at JPMorgan Chase & Co in New York City, working on-site. She is conducting research on natural language processing-related problems. Her advisor is Ismini Lourentzou.
Makanjuola Ogunleye, a Ph.D student in computer science, is a data scientist intern at Intuit, working remotely with the AI Capital team in Mountain View, California. The team is building a natural language processing and AI framework to improve the company’s risk assessment strategy and policy that will be added as a reusable service to the Intuit AI core capital group. His advisor is Ismini Lourentzou.
Medha Sawhney, a master’s degree student in computer science, is a machine learning engineering intern at Twitter in San Francisco, California, working remotely with the Health ML Team. Her advisor is Anuj Karpatne.
Avi Seth, a master’s degree student in computer science, is a data scientist intern at Gastrograph AI in New York City, working remotely on generalizing the preference prediction model for flavor profiles across different demographics. His advisor is Ismini Lourentzou.
Afrina Tabassum, a Ph.D. student in computer science, is an intern at Los Alamos National Laboratory (LANL) in New Mexico, working remotely. She is exploring machine learning techniques under varying data quality. Her advisor is Hoda Eldardiry.
Mia Taylor, a master’s degree student in computer science, is a graduate research engineer intern at Graf Research in Blacksburg, Virginia, working on-site. She is conducting applied machine learning research in a hardware context. Her advisor is Chris North.
Muntasir Wahed,a Ph.D. student in computer science, is a research intern at IBM Research – Almaden in San Jose, California, working on-site with the Intelligence Augmentation Group on set expansion techniques to build lexicons for natural language processing tasks. His advisor is Ismini Lourentzou.
Sijia Wang, a Ph.D. student in computer science, is an applied science intern at Amazon Web Services in New York City, working on-site on information extraction, entity linking, and related natural language processing tasks. Her advisor is Lifu Huang.
Xinyue Wang,a Ph.D. student in computer science, is a research intern on the Media Science Team at Yahoo, in San Jose, California, working on-site on a project related to trending user search queries and term refinement. His advisor is Edward Fox.
Zhiyang Xu, a Ph.D. student in computer science, is an applied scientist intern at Amazon Alexa AI in Sunnyvale, California, working on-site to detect the inconsistency of facts in dialog systems and improve the interpretability of the detecting process. His advisor is Lifu Huang.
Yi Zeng, a Ph.D. student in computer engineering, is an AI research intern at SONY Corporation of America in New York City, working remotely on developing a meta-learning-based method against general training data corruptions from a security perspective. His co-advisor is Ruoxi Jia.
Ed Fox, a professor of computer science and faculty member at the Sanghani Center for Artificial Intelligence and Data Analytics, is part of a research team tackling pressing questions about how global change will affect transmission of infectious disease between species, beginning with how rabies moves from vampire bats to other animals. Click here to read more.
At his June 6 update to the Virginia Tech Board of Visitors, Lance Collins, vice president and executive director of the Virginia Tech Innovation Campus, emphasized the appointment of 12 computer science and computer engineering faculty members to the campus team.
Collins further detailed the “faculty lead” positions, with several of the new faculty members accepting key leadership roles at the institution.
Naren Ramakrishnan, the Thomas L. Phillips Professor of Engineering and director of the Sanghani Center for Artificial Intelligence and Data Analytics, will serve as faculty lead for artificial intelligence and applied machine learning at the Innovation Campus. Read more here.
Hongjie Chen’s Ph.D. research in computer science lies in the areas of graph neural networks, time-series analysis, and recommendation systems.
“More specifically, I am currently working on time-series forecasting which is really useful in everyday life,” Chen said. “I am targeting accurate workload prediction in Cloud computing nodes.”
He said he was drawn to the Sanghani Center for its exciting advanced research atmosphere and excellent teaching faculty. He is advised by Hoda Eldardiry.
In August 2021 he presented collaborative work with researchers at Adobe Research (where he interned the summer before) and Eldardiry in proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD). Their paper, “Graph Deep Factors for Forecasting with Applications to Cloud Resource Allocation,” proposes a relational global model that learns complex non-linear time-series patterns globally using the structure of the graph to improve both forecasting accuracy and computational efficiency and that not only considers its individual time-series but also the time-series of nodes that are connected in the graph.
The experiments, Chen said, demonstrate the effectiveness of the proposed deep hybrid graph-based forecasting model compared to the state-of-the-art methods in terms of forecasting accuracy, runtime, and scalability,”
“Our case study reveals that GraphDF can successfully generate cloud usage forecasts and opportunistically schedule workloads to increase cloud cluster utilization by 47.5 percent on average,” he said.