Machine Learning Laboratory
RESEARCH
Multisource Machine Learning
The Machine Learning Laboratory research focuses on multisource and graph machine learning. We are developing graph-based deep learning techniques for natural language processing, time-series prediction and control. We develop our research in the context of various applications including cyber security, computer vision, healthcare and AI ethics.
Vision
To improve learning robustness, we develop multisource learning techniques including:
- (1) learning from external knowledge (prompts, interdependency structure, data augmentation)
- (2) multimodal learning (text, image, video, audio, sensor)
- (3) multimodel learning (reinforcement, few/zero-shot, relational, federated, supervised/unsupervised/semi-supervised)
- (4) hybrid learning (data-driven, model-based)
Research
- Multisource Learning for Natural Language Relation Extraction
- Multisource Learning for Timeseries Prediction
- Multisource Learning for Control
Applications
RESEARCH TEAM
Director
Students
PhD advisees
MS advisees
Alumni
MS Alumni
- Vasanth Reddy Baddam MS 2022 - Now a PhD Student @ our lab
- Chenhan Yuan MS 2021 - Now a PhD Student @ University of Manchester
- Milad Afzalan MS 2020 - Now an AI Researcher @ Schneider Electric
Undergraduate Alumni
- Yuan Chen - BS 2021 - Now a Masters Student at Rice University
- Joshua Matthew - Undergraduate researcher
- Tran Chau - Undergraduate researcher
- Mia Taylor - BS 2021 - Now a Masters Student at Virginia Tech
Student News
Conference Presentations
- Dec ‘22 - Chenhan presented our paper at IEEE International Conference on Big Data 2022: Clustering-based Unsupervised Generative Relation Extraction.
- Jun ‘22 - Vasanth presented our paper at the American Control Conference (ACC): Singular Perturbation-based Reinforcement Learning of Two-Point Boundary Optimal Control Systems.
- Feb ‘22 - Vasanth presented our paper at AAAI Workshop on Reinforcement Learning in Games: Cooperation Learning in Time-Varying Multi-Agent Networks.
- Dec ‘21 - Hongjie presented our paper at IEEE International Conference on Big Data 2021: Context Integrated Relational Spatio-Temporal Resource Forecasting.
- Dec ‘21 - Jiaying presented our paper at ICONIP 2021: Multistage Hybrid Attentive Networks for Knowledge-Driven Stock Movement Prediction.
- Nov ‘21 - Chenhan presented our paper at EMNLP 2021: Unsupervised Relation Extraction: A Variational Autoencoder Approach.
- Nov ‘21 - Jiaying presented our paper at CIKM 2021: Zero-shot Relation Classification from Side Information.
- Aug ‘21 - Hongjie presented our paper at KDD 2021: Graph Deep Factors for Forecasting with Applications to Cloud Resource Allocation.
- Jun ‘21 - Jiaying presented our paper at EANN 2021: Predicting Stock Price Movement Using Financial News Sentiment.
Final Defense
- Dec ‘22 - Vasanth defended his MS. thesis: Singular Perturbation-based Reinforcement Learning of Two-Point Boundary Optimal Control Systems.
- Apr ‘21 - Chenhan defended his MS. thesis: N-ary Cross-sentence Relation Extraction: From Supervised to Unsupervised Learning.
- Jun ‘20 - Milad defended his MS. thesis: Household electricity load shape segmentation from smart meter data based on temporal pattern and power magnitude.
Internships
- May ‘22 - Afrina started her internship at Los Alamos National Laboratory.
- May ‘22 - Jiaying started her internship at Rakuten.
- May ‘21 - Vasanth started his research internship at Siemens.
- Jun ‘20 - Hongjie started his research internship at Adobe Research.
- Jun ‘20 - Afrina started her research internship at the University of Virginia Biocomplexity Institute.
- May ‘20 - Mia started her internship at Amazon Web Services (AWS).
Alumni Adventures
- Sep ‘21 - Chenhan started his PhD at University of Manchester.
- Jul ‘20 - Milad joined ENGIE North America as a Data Scientist.
