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.
Theo Lim, an assistant professor of urban affairs and planning at Virginia Tech, is leading a research team studying ways that people can survive, adapt, and thrive through high temperatures and heat waves.
Each year, heat waves kill more Americans than any other natural disaster. Climate change has exacerbated the problem by creating measurably higher temperatures in areas of cities with fewer economic and social resources to mitigate the impacts of heat, according to Theo Lim, an assistant professor of urban affairs and planning at Virginia Tech.
Lim is leading a multidisciplinary Virginia Tech research team that is partnering with the City of Roanoke to help residents survive, adapt, and thrive through high temperatures and heat waves.
The six-person team received a Stage 1 Civic Innovation Challenge (CIVIC) Planning Grant, funded by the National Science Foundation. The challenge supports rapid implementation of community-driven, research-based pilot projects that address heat resilience priorities.
(From left) Lifu Huang, assistant professor of computer science and faculty at the Sanghani Center is advising a team of Ph.D. students — Minqian Liu, Ying Shen, Zhiyang Xu, and Barry Yao — competing in the Alexa Prize SocialBot Grand Challenge 5 sponsored by Amazon.com Services LLC. Photo by Jingyuan Qi.
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.
Graphic is from the paper, “Case Study Comparison of Computational Notebook Platforms for Interactive Visual Analytics”
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.”
On October 16, Liu will present a short paper, “Case Study Comparison of Computational Notebook Platforms for Interactive Visual Analytics,” at the Visualization in Data Science (VDS) Symposium associated with IEEE VIS 2022 in Oklahoma City.
He is on track to graduate this semester (FALL 2022) and his ultimate goal “is to become a data scientist who can analyze data for actionable insights and help people by solving real-world problems.”
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.”
Huimin Han, a master’s degree student in computer science, is spending the summer in Sunnyvale, California, for an internship at LinkedIn
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.
Virginia Tech broke ground on Academic Building One of the Innovation Campus in Alexandria in September. The campus’ first building will be 300,000 square feet and 11 stories tall when completed in 2024.
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.
Graphic is from the paper “Graph Deep Factors for Forecasting with Applications to Cloud Resource Allocation”
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.
Chen earned a bachelor’s degree in computer science from Xiamen University, China. He is projected to graduate in 2024 and would like to continue working in the field of time-series analysis.
And she is part of the Virginia Tech team from the Sanghani Center that is one of 10 finalists chosen to compete in the Alexa Prize SimBot Challenge. The challenge focuses on advancing the development of next-generation virtual assistants that continuously learn and gain the ability to perform common sense reasoning to help humans complete real-world tasks.
Wang’s specific role on the team — advised by Lifu Huang, who is also her academic advisor — is to establish knowledge graphs from instructional articles, images, and video demonstrations on the internet, such as WikiHow. She will also concentrate on collectively grounding entities and actions extracted from text to video to associate each entity or action with a visual image or video clip.
In her research, Wang focuses on natural language processing and machine learning, particularly information extraction with full or limited supervision.
Information extraction, she said, poses challenges because of its sophisticated annotation needs and variance benchmarks, she said.
“I am trying to automatically extract structured information from unstructured data,” Wang said. “For example, in the sentence ‘Melony was married just a month before she left for Iraq,’ the word ‘she’ indicates Melony, and her marriage occurs before the movement event. My research focus is to extract this information from the input sentence.”
Wang said that as a young child she wanted to understand foreign languages but knew that it would take a great effort to do so. “When I learned about machine learning as an undergraduate student, I was really drawn to it because of how we can use its model fitting and pattern learning abilities to automatically understand visual content.”
Wang holds a bachelor’s degree in vehicle engineering from Southwest Jiaotong University in China and a master’s degree in computer science from Washington University in St. Louis. She was drawn to Virginia Tech and the Sanghani Center for a Ph.D. computer science program because of the experienced professors and their cutting-edge research in artificial intelligence and data science. “Their work and achievements and all the passionate students around me have motivated me to work harder,” she said.
Being a Ph.D. student has made her realize how much time and effort it takes to become a successful academic researcher, she said. “So after graduation, I will be looking for a postdoc position or other research opportunities at private and research labs to become better equipped to become a research scientist.”
