Sanghani Center Student Spotlight: Hongjie Chen

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.

Another collaborative paper, “Context Integrated Relational Spatio-Temporal Resource Forecasting,” was published at the 2021 IEEE International Conference on Big Data.

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.

Sanghani Center Student Spotlight: Sijia Wang

Graphic is from the paper “Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding”

The Spring 2022 semester was a memorable one for Ph.D. student Sijia Wang.

The Association for Computational Linguistics (ACL) accepted the paper, “Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding,” which she is presenting on May 24 during its international meeting in Dublin. 

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.”

Wang is projected to graduate in 2024.

Virginia Tech alumna named ethics co-chair for leading conference in artificial intelligence and machine learning

Cherie Poland earned a Master of Engineering from the Department of Computer Science’s first new graduate program for the Virginia Tech Innovation Campus. Photo courtesy of Cherie Poland

Virginia Tech alumna Cherie Poland has been named one of four ethics co-chairs for the 36th Conference on Neural Information Processing Systems (NeurIPS), the most prestigious conference in artificial intelligence and machine learning (AI/ML).  

This is the latest entry on Poland’s list of achievements. To name only a few, she was issued one European patent and had five of her U.S. patent applications filed; created and later sold a biotech company; ran her family-owned cattle ranch (while holding a full-time position as a biotech patent examiner at the U.S. Patent and Trademark Office); and earned six college degrees, including a J.D.

The most recent, in December 2021, is from Virginia Tech, where she was a student at the Sanghani Center for Artificial Intelligence and Data Analytics. She received a Master of Engineering from the Department of Computer Science, one of the first degree programs for the university’s Innovation Campus. Read more about Poland here.

Congratulations to Sanghani Center Spring 2022 Graduates

Spring 2022 Commencement ceremonies and related events are under way on Virginia Tech campuses in Blacksburg and in the greater metropolitan D.C. area. 

“We celebrate our graduates who have persevered over hurdles raised by the Covid pandemic to reach their academic goals. For longer than anyone would have suspected at the onset of the pandemic, this group of students had to adapt to a virtual environment. Online, they attended classes, met with their advisors, conducted research, presented papers at conferences, and worked at internships,” said  Naren Ramakrishnan, the Thomas L. Phillips Professor of Engineering in the Department of Computer Science at Virginia Tech and director of the Sanghani Center for Artificial Intelligence and Data Analytics. “We are proud of all they have accomplished during their years at the center and wish them continued success as they begin their professional careers.”

Following is a list of Sanghani Center graduates:


Chidubem Arachie, advised by Bert Huang, has earned a Ph.D. in computer science. His research interest lies in developing algorithms for weakly supervised learning. The title of his dissertation is “Learning with Constraint-Based Weak Supervision.” Arachie is joining Google in California as a software engineer.

Yali Bian, advised by Chris North, has earned a Ph.D. in computer science. His research interests include human-computer interaction, visual analytics, machine learning, and machine teaching. The title of his dissertation is “Human-AI Sensemaking with Semantic Interaction and Deep Learning.” Bian is joining the Human and AI Systems Research (HAR) Lab at Intel Labs, Santa Clara, California, as a research scientist. 

Subhodip Biswas, advised by Naren Ramakrishnan, has earned a Ph.D. in computer science. His primary research lies in spatial data mining, geographic information systems, education, and crowdsourcing. The title of his dissertation is “Spatial Optimization Techniques for Redistricting.” He has also earned a graduate certificate in urban computing. Biswas is joining the AI verification team at the autonomous vehicle company Zoox in Foster City, California.

Debanjan Datta, advised by Naren Ramakrishnan, has earned a Ph.D. in computer science. Datta’s research focus is on data mining and machine learning, with a special interest in algorithms on anomaly detection and tabular data. The title of his dissertation is “A Framework for Automated Discovery and Analysis of Suspicious Trade Records.” Datta is joining Amazon Web Services (AWS) as an applied scientist.

Chen Gao, advised by Jia-Bin Huang, has earned a Ph.D. in electrical and computer engineering. His research interest lies in the field of computational photography and computer vision. He is focusing on view synthesis and video manipulation. The title of his dissertation is “Learning Consistent Visual Synthesis.” Chen will be joining Meta in Seattle, Washington, as a research scientist.

Taoran Ji, advised by Chang-Tien Lu, has earned a Ph.D. in computer science. His research interests include natural language processing, text mining, and machine learning. The title of his dissertation is “On Modeling Dependency Dynamics of Sequential Data: Methods and Applications.” Ji has joined Moody’s Analytics in New York, as director, artificial Intelligence and machine learning. 

Xiaolong Li, advised by Lynn Abbott, has earned a Ph.D. in electrical and computer engineering. His primary research interest is in the area of computer vision, with a special focus on deep 3D representations learning toward dynamic scene understanding. The title of his dissertation is “3D Deep Learning for Object-Centric Geometric Perception.” Li is joining AWS AI in Seattle, Washington, as an applied scientist.

Yuliang Zou, advised by Jia-Bin Huang, has earned a Ph.D. in electrical and computer engineering. His research interest lies in designing label-efficient and/or robust visual understanding methods. The title of his dissertation is “Label-Efficient Visual Understanding with Consistency Constraints.” Zou is joining Waymo, an autonomous driving technology company in Mountain View, California, as a research scientist.

Master’s Degree

Larissa Basso, advised by Chang-Tien Lu, has earned a master’s degree in computer science. Her primary research focus is satellite image retrieval. The title of her thesis is “CLIP-RS: A Cross-modal Remote Sensing Image Retrieval Based on CLIP, Northern Virginia Case Study.” 

Chih-Fang Chen, advised by Chang-Tien Lu, has earned a master’s degree in computer science. His primary research interest is urban computing. The title of  his thesis is “Metrohelper: A Real-time Web-based System for Metro Incidents Detection Using Social Media.” Chen is joining Amazon as a software developer engineer.

Kai-Hsiang Cheng, advised by Chang-Tien Lu, has earned a master’s degree in computer science. His primary research interests are applied machine learning and data mining. The title of  his thesis is “Leverage Fusion of Sentiment Features and Bert-based Approach to Improve Hate Speech Detection.” Cheng is joining Gettr in New York City as software developer.

Riya Daniadvised by Ismini Lourentzou, has earned a master’s degree in computer science. Her primary research involves generating videos of unseen concepts using machine learning. The title of her thesis is “Concept Vectors for Zero-Shot Video Generation.” Dani is joining Amazon Web Services (AWS) in Northern Virginia as an associate solutions architect.

Xuan Li, advised by Lynn Abbott, has earned a master’s degree in electrical and computer engineering. His research focuses on continual learning that prevents a deep neural model from catastrophic forgetting in sequential tasks. The title of his thesis is “Referencing Unlabelled World Data to Prevent Catastrophic Forgetting in Class-incremental Learning.” Li is joining Amazon as software development engineer.

Gopikrishna Rathinavel, advised by Naren Ramakrishnan, has earned a master’s degree in computer science. His research focus is on using deep learning techniques for wireless anomaly detection. The title of his thesis is “Detecting Irregular Network Activity with Adversarial Learning and Expert Feedback.”

Stephen Sun, advised by Chang-Tien Lu, has earned a master’s degree in computer science. His primary research interest is social media analytics. The title of his thesis is “Estimate Flood Damage Using Satellite Images and Twitter Data.” Sun is joining TikTok Inc. in Mountain View, California, as a software engineer.

Han Xu, advised by Lynn Abbott, has earned a master’s degree in electrical and computer engineering. His research focuses on skin segmentation without color information. The title of his thesis is “Color Invariant Skin Segmentation.” 

Mehul Sanghani to deliver College of Engineering commencement address as Distinguished Alumni Speaker

Mehul Sanghani. Photo courtesy of Chuck Kennedy.

As founder and CEO of Octo, a technology and consulting firm focused on using emerging technologies to solve the federal government’s most challenging problems, Mehul Sanghani ’98 is no stranger to opportunity, sacrifice, and even regret. He’ll impart these messages and others to graduates of Virginia Tech’s College of Engineering as the Distinguished Alumni Speaker for the spring 2022 commencement ceremonies on May 14. Read more about his life and philanthropy — including a generous endowment for the Sanghani Center for Artificial Intelligence and Data Analytics here.

Twelve Virginia Tech faculty join Innovation Campus

Twelve highly accomplished Virginia Tech faculty experts in computer science and computer engineering have formally affiliated with the Virginia Tech Innovation Campus in Alexandria. This first cohort of Innovation Campus faculty will play a vital role in shaping the new campus by helping to establish key research themes, enhancing the project-based curriculum, and developing the campus governance structure. Among these 12 experts are Naren Ramakrishnan, Thomas L. Phillips Professor of Engineering and director of the Sanghani Center for Artificial Intelligence and Data Analytics and center faculty Chang-Tien Lu, professor of computer science and director of the computer science program, Northern Virginia. Read more here.

Sanghani Center Student Spotlight: Mandar Sharma

Graphic is from the paper “T3: Domain-Agnostic Neural Time-series Narration”

Would you like a virtual assistant that could go through chunks of large reports with pages upon pages of tables and raw numeric data and summarize it all in a short paragraph? 

This is what Mandar Sharma is trying to accomplish with his Ph.D. research in the area of natural language generation.

“The progress of artificial intelligence depends heavily upon our ability to communicate with machines and natural language is the crux of human communication,” Sharma said. The paper, “T3: Domain-Agnostic Neural Time-series Narration,” which he presented at the 2021 IEEE International Conference for Data Mining, generates succinct narratives that describe large time-series datasets.

“With a dataset of time-series and narrative pairs, a promising direction for future exploration lies in learning direct mappings from numbers to text, extending beyond just time-series,” said Sharma, who is advised by Naren Ramakrishnan.

Continue reading…

CI Fellow Rebecca Faust brings expertise on human-AI interaction methods for dimension reduction to Sanghani Center work with Chris North

Rebecca Faust

A 2021 Computing Innovation (CI) Fellow, postdoc Rebecca Faust, has been working with Chris North, professor in computer science and associate director at the Sanghani Center for Artificial Intelligence and Data Analytics, since January.

They are exploring how to create explanations of the effects of semantic interactions on a deep learning model through the analysis of perturbations and differences in the model after interactions. 

“Through these explanations, we hope to demonstrate how models adjust when people inject prior knowledge into them through semantic interaction and validate whether the updated model adequately captures this prior knowledge,” said Faust, who earned her Ph.D. in computer science from the University of Arizona in December 2021. 

Faust will also help lead Department of Defense (DoD)-funded projects on interactive analytics, funded through the Center for Space, High-Performance, and Resilient Computing (SHREC).

“Dr. North was at the top of my list,” she said. “Together, we crafted an application, including a research proposal, a fellowship plan, and a mentorship plan, and submitted it to the program.” 

Continue reading…

Virginia Tech and Amazon establish machine learning research partnership

January 21, 2020 – Students and faculty of the Data Analytics Center work together at the Virginia Tech Research Center – Arlington. (Photo by Erin Williams/Virginia Tech)

Virginia Tech and Amazon are partnering to advance research and innovation in artificial intelligence and machine learning. The Amazon – Virginia Tech Initiative for Efficient and Robust Machine Learning will include machine learning-focused research projects, doctoral student fellowships, community outreach, and an establishment of a shared advisory board.

“This partnership affirms the value of our connection to Amazon as we scale up project-based learning and research programs in artificial intelligence and machine learning,” said Virginia Tech President Tim Sands. “Building Virginia Tech’s strength and expertise in these fields will support critical technological advancements and our commitment to fuel workforce development in the commonwealth.” 

“We are delighted to collaborate with Virginia Tech in launching this new initiative which brings together the top talent in our two organizations in a joint mission to achieve ground-breaking advances in robust machine learning,” said Prem Natarajan, vice president of Alexa AI – Natural Understanding at Amazon. “The proximity of this initiative to Amazon’s HQ2 will catalyze research efforts that leverage the depth of talent in the Northern Virginia area to address some of the most pressing challenges in AI.” Click here to learn more about the initiative which will be housed in the College of Engineering and led by Sanghani Center for Artificial Intelligence and Data Analytics researchers.

Scientists partner on multi-university grant to establish a field of ‘imageomics’

The Imageomics Institute will create a new field of study that uses images of living organisms to understand biological life processes.

Researchers in three different disciplines at Virginia Tech are partnering in a $15 million grant from the National Science Foundation (NSF) to establish an institute in the new field of “imageomics,” aimed at creating a new frontier of biological information using vast stores of existing image data, such as publicly funded digital collections from national centers, field stations, museums, and individual laboratories. 

The goal of the institute is to characterize and discover patterns or biological traits of organisms from images and gain insights into how function follows form in all areas of biology. It will expand public understanding of the rules of life on Earth and how life evolves.

Imageomics is one of five Harnessing the Data Revolution institutes receiving support from the NSF.  

Anuj Karpatne, assistant professor in the Department of Computer Science and faculty at the Sanghani Center for Artificial Intelligence and Data Analytics, is serving as one of four co-investigators for the multi-university project led by the Ohio State University. Leanna House, associate professor in the Department of Statistics and faculty at the Sanghani Center, and Josef Uyeda, assistant professor in the Department of Biological Sciences, are designated senior personnel. All three researchers are part of the executive leadership team of the institute and investigators on Virginia Tech’s $1.4 million portion of the grant. Click here to read more about these scientists will apply their expertise to the project.