Below is a list of labs affiliated with ML@GT. This is not a comprehensive list. To find more information on our labs, please look at our Ph.D. Program Faculty and faculty list to find a faculty member who aligns with your research interests.
Artificial Intelligence Labs
- Led by Polo Chau
- We innovate scalable, interactive, and interpretable tools that amplify human's ability to understand and interact with billion-scale data and machine learning models. Our current research thrusts: human-centered AI (interpretable, fair, safe AI; adversarial ML); large graph visualization and mining; cybersecurity; and social good (health, energy).
- Led by Mark Riedl
- We work on human-centered AI research that requires understanding people to make progress on hard problems. Entertainment--storytelling, games, etc.--provides a lens into how AI systems can interact with humans in open-ended ways, though we do serious stuff too, such as AI explainability, AI safety, and ethics.
- Led by B. Aditya Prakash
- Our core research interests are in data science, machine learning and AI. However, we are motivated by highly challenging real world problems, especially as they arise in computational epidemiology, public health, critical infrastructure/urban computing, cybersecurity and the Web. We approach these applications from a data-driven viewpoint, and invent new inter-disciplinary methodologies bridging models/domain knowledge (e.g. disease models) with data (e.g. surveillance). We work closely with domain experts in these topics and design novel methods and tools cutting-across network science, combinatorial and stochastic optimization, data mining, AI and simulation areas.
- Led by Ghassan AlRegib
- At OLIVES (Omni Lab for Intelligent Visual Engineering and Science), we work on advancing machine learning and AI for applications where consistent labels are scarce and users' inputs are vital. Our work is on creating a model that is riobust, adapts to new and different data, reliable, and generalizable. Topics include: Explainable AI, Robust Learning, Active Learning, Weakly Supervised Learning, Anomaly Detection, Contrastive Learning, and Zero Shot learning. Applications include computer vision, AVs, and Healthcare.
Network Science Lab
- Led by Constantine Dovrolis
- Network Science, Network Neuroscience, Neuro-inspired AI
- Led by Devi Parikh
- Research interests are in computer vision, natural language processing, embodied AI, human-AI collaboration, and AI for creativity.
- Led by Dhruv Batra
- Interested in artificial intelligence (AI). More specifically, my research lies at the intersection of machine learning and computer vision, with forays into natural language processing.
- The long-term goal of my research is A-STAR: agents that
- see (or more generally perceive their environment through vision, audition, or other senses),
- talk (i.e. hold a natural language dialog grounded in their environment),
- act (e.g. navigate their environment and interact with it to accomplish goals), and
- reason (i.e., consider the long-term consequences of their actions).
Computational Biology Labs
Zhang's CompBio Lab
- Led by Xiuwei Zhang
- We develop machine learning methods to analyze large scale biological data, especially data at single cell level to understand mechanisms in cell development and diseases.
Computer Vision Labs
- Led by Jim Rehg
- We conduct basic research in computer vision and machine learning, and work in a number of interdisciplinary areas: developmental and social psychology, autism research, mobile health, and robotics. The study of human social and cognitive behavior is a cross-cutting theme.
- Led by Irfan Essa
Data Science Labs
- Led by Srijan Kumar
- We work on creating data science and AI solutions to solve important problems on the web and in society.
- Led by Jing Li
- We develop Machine Learning and Artificial Intelligence algorithms for modeling and inference of complex-structured datasets with high dimensionality (e.g., 3D/4D images), multi-modality, and heterogeneity. We focus on providing capacities for monitoring & change detection, diagnosis, and prediction & prognosis. The application domains mainly include health and medicine, focusing on medical image data analytics as well as fusion of images, genomics, clinical records, and mobile health datasets for personalized and precision medicine.
- Led by Sudheer Chava
- Georgia Tech’s Financial Services Innovation Lab is located in the heart of the Technology Square Innovation ecosystem. The FinTech lab aims to be a hub for finance education, research and industry in the Southeast. The lab acts as a platform to connect and bring together faculty and students across Georgia Tech with the financial services industry and FinTech entrepreneurs.
- Led by Morris Cohen
- Forecasting of space weather disruptions to the power grid, GPS, and communications, merging ML models with physics-based models of the Sun-Earth system.
Machine Learning Theory Labs
- Led by Yao Xie
- Modeling spatio-temporal data, sequential data, and performing statistical inference (such as online anomaly detection, estimating dynamic networks)
- Led by Xiaoming Huo
- We study theory in machine learning and statistical learning methods, as well as the foundation of data science.
- Led by Tuo Zhao
- My group focuses on (1) theoretical foundations of machine learning, especially deep learning and (2) neural language models, especially under low resource settings.
Statistical Machine Learning Lab
- Led by Ashwin Pananjady
- We are interested in multiple aspects of the modern data science pipeline, unified broadly under the theme of statistical theory and methodology. Our research involves both the modeling of complex, high-dimensional data arising in a variety of applications, and the design and analysis of efficient algorithms for drawing principled inferences from such data. Our projects engage with and improve upon tools used in statistics, optimization, and information theory, with a specific focus currently on statistical and computational issues arising in reinforcement learning, human-in-the-loop systems, and structured signal processing.
GT Dynamical Machine Learning Lab
- Led by Molei Tao
- We are interested in things in machine learning that are changing (i.e. dynamics). Examples: the training of a machine learning model is dynamical; how input propagates to output in deep/wide neural networks is dynamical; in diffusion generative models, both the forward noising process and backward denoising process are dynamical; games are dynamica; and so is data!
Natural Language Processing Labs
- Led by Diyi Yang
- Georgia Tech's Social and Language Technologies (SALT) lab studies Social NLP. Broadly, we research both content and social aspects of human language (e.g., what is said, who says it, in what context, for what goals), via methods of natural language processing, deep learning, and machine learning as well as theories in social science and linguistics, with the implications of developing interventions to facilitate human-human and human-machine communication.
- Led by Alan Ritter
- Led by Wei "Coco" Xu
- Research lies at the intersections of machine learning, natural language processing, and social media. I focus on designing algorithms for learning semantics from large data for natural language understanding, and natural language generation in particular with stylistic variations.
FATHOM Research Group
- Led by Swati Gupta
- Optimization, Machine Learning, and Algorithmic Fairness
- Led by Siva Theja Maguluri
- We work on developing a theoretical understanding of Reinforcement Learning (RL) algorithms using finite time guarantees. These tools are used to design novel RL algorithms.
- Led by Mark Davenport
- Led by Zsolt Kira
- Our work is in the intersection of learning methods for sensor processing and robotics, developing novel machine learning algorithms and formulations towards solving some of the more difficult perception problems in these areas. We are especially interested in moving beyond supervised learning (un/semi/self-supervised and continual/lifelong learning), integration of learning and acting/planning, and distributed perception (multi-modal fusion, learning to incorporate information across a group of robots, etc.).
- Led by Frank Dellaert
- Group works on selected topics on the intersection between computer vision and robotics.