Machine, Deep and Reinforcement Learning
Explore our Research Topics
|
Jing Li |
Research Areas: Real-time systems, parallel computing, cyber-physical systems and reinforcement learning for system design and optimization Reinforcement Learning-Based System Design The design space of modern complex systems is increasingly large. Finding good designs often involves solving mixed-integer optimization problems that are highly intractable. Our research develops reinforcement learning-based frameworks with graph neural networks and active learning techniques to intelligently and efficiently find good designs from the huge design space. We have applied our frameworks to various system design tasks, including resource allocation in cyber-physical systems and circuit design.
|
|
|
Usman Roshan |
Research Areas: Machine learning, medical informatics Adversarial Robust Machine Learning With 0-1 Loss: Machine learning models today are highly accurate but not very robust. They can be fooled to misclassify data with minor perturbations known as adversarial attacks. Adversaries targeting a given convex model are known to affect other convex models. We find this transferability phenomenon to be less effective between 0-1 loss and convex losses such as hinge and logistic, both of which are approximations to 0-1 loss and known to |
|
|
Hai Phan |
Research Areas: Social network analysis, machine learning, spatio-temporal data mining Ontology-Based Interpretable Deep Learning Machine learning models are trained with large amounts of data and achieve a certain level of competency in interpreting and classifying new input data. However, even if they work well, it can be difficult to explain why. Lingering doubt persists that, in some situations, the classification output of the model might be wrong. In applications such as self-driving cars, this could have spectacularly negative consequences. We tie predictions of the model to a set of keywords taken from a predefined vocabulary of relevant terms. The number of words hard-coded into the model that influence the outcome produced by a machine learning for a new input is reduced and those words are taken from a limited and relevant ontology. This makes the output of the model easier to interpret as it becomes independent from terms that are irrelevant to the application domain. |
|
|
Guiling “Grace” Wang |
Research Areas: Deep learning, FinTech, blockchain technologies, intelligent transportation systems Deep Reinforcement Learning for Intersection Control Reinforcement Learning-based traffic signal controllers can adaptively adjust signals based on real-time demand. To learn a good policy, we have proposed combining a dueling network, target network and double Q-learning network with prioritized experience replay technology in one signalized intersection. It has proven to be a successful attempt to stabilize the learning process and mitigate over-estimations of the learning agent. To further guarantee the safety of vehicles, we have incorporated domain safety standards in the above RL-based traffic signal controller. Nonetheless, the small proportion of the collision data makes this problem extremely challenging, not to mention that the learning agent might not obey the safety rules in practice. We thus, instead of letting the RL model learn by itself, incorporate domain safety standards into different parts of the RL model (i.e., action, state, loss function and reward function) as a safety shield. This safety-enhanced approach can guide and correct the RL agent toward learning a much safer action and dramatically lower the collision rate. Meanwhile, we not only focus on one intersection but also consider multiple intersections as a network to make a smoother driving experience. By enabling cooperation among intersections, each RL agent learns to communicate with others to spread out the traffic pressure quickly. Intensive experiments show the effectiveness of our systems. |
|
|
Lijing Wang |
Research Areas: Machine learning, deep learning, natural language processing Fine-Tuning for Improved Bias and Variance for Information Extraction The bias-variance tradeoff is the idea that learning methods need to balance model complexity with data size to minimize both under-fitting and over-fitting. Recent empirical work and theoretical analysis with over-parameterized neural networks challenges the classic bias-variance trade-off notion. We are exploring a variance decomposition-based justification criteria to examine whether large pretrained neural models (e.g., RoBERTa) in a fine-tuning task are generalizable enough to have low bias and variance. |
|
|
Zhi Wei |
Research Areas: Machine learning, statistical modeling, bioinformatics Explainable AI for Unsupervised Learning In recent years, explanation techniques have emerged and received a lot of attention. In supervised learning settings, it emphasizes the ability to correctly interpret a prediction model’s output. Most existing explanation works have been focused on supervised learning, such as LIME and SHAP. Yet very little work has been done in an unsupervised learning setting. Our goal is to explain why and how a sample is assigned to a specific cluster in unsupervised learning. Specifically, we would like to know which features are portrayed as contributing to a cluster, or evidence against it. With this information, a practitioner can make an informed decision about whether to trust the model’s cluster assignment. There is also a so-called “double use of data” problem when trying to find discriminative features that distinguish the resultant clusters. We will apply the new methods to analyze finance and accounting data. |
|
|
Jason Wang |
Research Areas: Data mining, machine learning, deep learning, explainable AI, generative AI, data science Cyberinfrastructure-Enabled Interpretable Machine Learning Cyberinfrastructure (CI) enabled machine learning refers to new computing paradigms such as machine-learning-as-a-service (MLaaS), operational near real-time forecasting systems, and predictive intelligence with Binder-enabled Zenodo-archived open-source machine learning tools, among others. These computing paradigms take advantage of advances in CI technologies, incorporating machine learning techniques into new CI platforms. In this project we focus on interpretable machine learning where we attempt to explain how machine learning works, why machine learning is powerful, what features are effective for machine learning, and which part of a testing object is crucial for a machine learning model to make its prediction. Methods, techniques, and algorithms developed from this project will contribute to advancements of CI-enabled predictive analytics and explainable artificial intelligence in general. |
|
|
Mengnan Du |
Research Areas: Trustworthy machine learning, deep learning, natural language processing Trustworthy and Responsible Machine Learning Trustworthy machine learning has emerged as a critical area of study as machine learning models become increasingly ubiquitous and influential in diverse domains. As these systems are tasked with making consequential decisions that impact individuals and societies, it is imperative to ensure their transparency, fairness, and robustness. Lack of transparency can lead to opaque decision-making processes, while biases and discrimination can perpetuate harmful societal inequalities. Furthermore, the vulnerability of models to adversarial attacks or distributional shifts can undermine their reliability and compromise their intended functioning. To address these pressing challenges, we delve into the extensive domain of trustworthy machine learning, with a particular emphasis on crucial aspects such as explainability, fairness, and robustness. Notably, we also investigate trustworthy large language models (LLMs), with a focus on unlocking the full potential of LLMs while addressing their unique challenges in terms of trustworthiness and responsibility. |
|
