News

Virginia Tech and Amazon gathered for a Machine Learning Day held at the Virginia Tech Research Center — Arlington on April 25 to celebrate and further solidify their collaborative Amazon–Virginia Tech Initiative for Efficient and Robust Machine Learning.  

Announced last year, the initiative — 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 — supports 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 full story here.

Afrina Tabassum, a Ph.D. student in computer science, was attracted to the Sanghani Center by the trending research conducted by faculty for improving machine learning algorithms and their application to other fields.

Her research interests lie in machine learning and self-supervised learning, particularly designing novel representation learning objectives for multi-modal data. “I was really attracted to this area of research by an urge to use deep learning in order to make people’s lives easier,” she said.

One of the projects Tabassum is working on at the Sanghani Center is “Hard Negative Sampling Strategies for Contrastive Representation Learning,” a collaboration with her advisors, Hoda Eldardiry and Ismini Lourentzou and a fellow Ph.D. student.

Their paper introduces Uncertainty and Representativeness Mixing (UnReMix) for contrastive training, a method that combines importance scores that capture model uncertainty, representativeness, and anchor similarity. 

“We verify our method on several visual, text and graph benchmark datasets and perform comparisons over strong contrastive baselines,” said Tabassum, “and to the best of our knowledge, we are the first to consider representativeness for hard negative sampling in contrastive learning in a computationally inexpensive way.”

Experimental and qualitative results so far have demonstrated the effectiveness of their proposed approach, she said.

Tabassum is also part of a team from Lourentzou’s PLAN Lab which is competing in the Alexa Prize Taskbot Challenge 2.

“Ten teams across the world were selected to build a taskbot to assist in cooking and performing other tasks around the house. Our bot will be able to make adaptable conversation a reality by allowing customers to follow personalized decisions through the completion of multiple sequential subtasks and adapt to the tools, materials, or ingredients available to the user by proposing appropriate substitutes and alternatives,” she said.

In addition to working on adapting instructions according to the user needs, she is serving as student team leader with responsibilities that include setting clear team goals and short-term deadlines and delegating tasks among all the team members. 

Projected to graduate in 2024, Tabassum would like to pursue a career in industry research.

A Virginia Tech team of  five computer science Ph.D. students at the Sanghani Center for Artificial Intelligence and Data Analytics is one of 10 university teams selected internationally to compete in the Alexa Prize TaskBot Challenge 2. The team will design multimodal task-oriented conversational assistants that help customers complete complex multistep tasks while adapting to resources and tools available to the user, such as ingredients or equipment. Read more here.

DAC Ph.D. student Chidubem Arachie is working remotely as an intern at Google Research.

A national pandemic that forced the closing of physical offices has not stopped graduate students at the Discovery Analytics Center from working remote internships at companies, research laboratories, and other institutions across the country. For many students, summer internships help further their own research as they gain real world experience.

Following is a list of DAC students and the work they are doing for the next few months:

Chidubem Arachie, a Ph.D. student in computer science, is a research intern at Google Research in Mountain View California. He is working on generative modeling for 3D shapes. His advisor is Bert Huang.

John Aromando, a Ph.D. student in computer science, is an intern at Graf Research in Blacksburg, working on utilizing natural language processing to support the software verification process. His advisor is Edward Fox.

Hongjie Chen, a Ph.D. student in computer science, is a data science research intern at Adobe in San Jose, California. He is on the Cloud Technology Team, researching cloud resource allocation strategy. His advisor is Hoda Eldardiry.

Nurendra Choudhary, a Ph.D. student in computer science, is an applied science intern with the Amazon Search Team in Palo Alto, California. He is working on representation learning of products by leveraging the heterogeneous relations between them. His advisor is Chandan Reddy.

Joshua Detwiler, a Ph.D. student in computer science, is an intern for the Navy in Dahlgren, Virginia, where he is working on a distributed application for network analysis. His advisor is Layne Watson.

Chen Gao, a Ph.D. student in electrical and computer engineering, is a research intern at Google in Mountain View, California. He is working on improvements to the portrait mode on the Google Pixel phone. His advisor is Jia-Bin Huang.

Akshita Jha, a Ph.D. student in computer science, is a research intern in the Interdigital AI Lab in Palo Alto, California. Her work involves building interpretable natural language processing models. Her advisor is Chandan Reddy.

Prerna Juneja, a Ph.D. student in computer science, is an intern at the Information Science Institute at the University of Southern California with Emilio Ferrara, assistant research professor and associate director of Applied Data Science in the Department of Computer Science. She is investigating the spread of COVID-19 related conspiracy theories on Twitter. Her advisor is Tanushree Mitra.

You Lu, a Ph.D. student in computer science, is a research intern at NEC Labs America in Princeton, New Jersey, working on sequence labeling for signals in fibers. His advisor is Bert Huang.

Shruti Phadke, a Ph.D. student in computer science, is doing a research internship with James Pennebaker, a professor in the Department of Psychology at the University of Texas at Austin. She is studying online communities, their social processes, and behaviors. Her advisor is Tanushree Mitra.

Aarathi Raghuraman, a master’s degree student in computer science, is an intern at GlaxoSmithKline (GSK), working with the Digital, Data, and Analytics team to maximize process yield in upstream biopharm manufacturing. She is advised by Lenwood Heath.

Esther Robb, a master’s degree student in electrical and computer engineering, is a research intern at Google working with a team in San Francisco on reinforcement learning. Her advisor is Jia-Bin Huang.

Mandar Sharma, a master’s student in computer science, is working as a machine learning intern with Toyota Motors North America, specifically the Toyota Racing Development (TRD) branch, to help NASCAR drivers make better decisions when they are racing. His advisor is Naren Ramakrishnan.

Aarohi Sumant, a master’s student in computer science, is an intern at Amazon. She is working with the Kindle Marketing Team to develop machine learning techniques for book recommendations based on cross user activities as well as single-user activities on different Amazon platforms. Her advisor is Edward Fox.

Afrina Tabassum, a Ph.D. student in computer science is a data science intern in the Data Science for The Public Good (DSPG) program at the Biocomplexity Institute’s Social and Decision Analytics Division (SDAD) at the University of Virginia. She is working on projects that address state, federal, and local government challenges around critical social issues relevant in the world today. Her advisor is Hoda Eldardiry.

Mia Taylor, a senior undergrad in computer science, is interning at Amazon Web Services in the Route 53 (DNS) service. Her advisor is Hoda Eldardiry.

Sirui Yao, a Ph.D. student in computer science, is an intern at Google, working on tag prediction for recommender systems through learning items and tags embeddings. Her advisor is Bert Huang.

Shengzhe Xu, a Ph.D. student in computer science, is interning at Facebook Ads Core ML, working on attention-based time sequential embedding aggregation. Xu’s advisor is Naren Ramakrishnan.

Ming Zhu, a Ph.D. student in computer science, is interning at Amazon. She is an applied scientist intern for Amazon Alexa AI, working on conversational query representation learning. Zhu’s advisor is Chandan Reddy.

Yuliang Zou, a Ph.D. student in electrical and computer engineering, is working on learning with less/weaker annotations at Google. His advisor is Jia-Bin Huang.