Colloquium talks will be held in the Katharine Reed Cudahy Building on the Marquette University campus. Please address inquiries/suggestions to Dr. Michael Zimmer.

Spring 2020 - Unless specified, the talks will begin at 1:00pm CT in Room 414 at Cudahy Hall.

  • Tuesday, January 14: Dr. Maia Jacobs (Center for Research on Computation and Society, Harvard)
    Title: One Size Doesn’t Fit Anyone: Tailoring Digital Tools for Personal Health Journeys
    Personal technologies for everyday health management have the potential to transform healthcare by empowering individuals to engage in their own care, scaffolding access to critical information, and supporting patient-centered decision-making. Currently, many personal health tools often focus only on a single task or isolated event. However, chronic illnesses are characterized by information needs and challenges that shift over time; thus, these illnesses are better defined as a dynamic trajectory than a series of singular events.
    In this talk, I discuss my work designing and implementing novel computing systems that: 1) support chronic illness trajectories and 2) reduce patients’ barriers to health information access. I’ll present my approach using personalized and adaptive content to connect individuals with timely and actionable feedback. Using results from longitudinal field deployments, I demonstrate the ability for these tools to facilitate patients’ proactive health management and engagement in their care. I’ll also discuss the utility of this approach for encouraging to long-term engagement with health tools, as evidenced by longitudinal usage patterns. I’ll conclude with opportunities for using personalization as a strategy to support other complex information tasks, including the health management of illness trajectories in which uncertainty is paramount and the integration of machine learning models into clinical workflows.
  • Wednesday, January 15: Saeed Tizpaz Niari (CS Department, CU Boulder) 
    Title: Differential Debugging for Side Channel Vulnerabilities
    In early 2018, Meltdown and Spectre attacks challenged the security of any computer devices globally. These attacks exploit timing information to compromise the confidential information of users. While most existing debugging techniques provide supports for the functional correctness, the support for non-functional properties such as information leaks via timing observations is scarce. In this talk, Tizpaz-Niari will showcase a range of tools and techniques to detect, explain, and mitigate side-channel vulnerabilities in large-scale libraries and web applications. The technique combines tools from gray-box fuzzing, dynamic program analysis, and machine learning inferences. The talk also presents a novel technique to adapt neural networks for quantifying the amounts of information leaks.
  • Thursday, January 16: Dr. Kevin Moran (Computer Science, William & Mary)                            Title: Toward Practical Automation for Software Engineering
    Given the ubiquity of software in modern society and its applications in increasingly complex problem domains, today’s developers require practical automation in order to effectively and efficiently build, test, and maintain software systems. At the same time, the proliferation of software has led to the creation of an unprecedented amount of freely available data that describes a diverse array of software systems. Artifacts such as source code files, screenshots, videos and bug reports provide a wealth of information from which patterns can be learned to enable useful automation for developers. In this talk, I will describe two of my recent research projects that use machine learning techniques to harness this data contained within software repositories to automate different components of the development lifecycle for mobile applications. My focus on mobile apps stems from the potential impact given the popularity of mobile platforms among both developers and users coupled with development challenges that are unique to the mobile domain (such as change-prone APIs and platform fragmentation). These projects aim to improve developer productivity while alleviating the effects of these challenges.
    First, I will introduce an approach that completely automates the process of prototyping of GUIs for mobile apps. This approach, called ReDraw, is able to transform an image of a mobile app GUI into runnable code by detecting discrete GUI-components using computer vision techniques, classifying these components into proper functional categories (e.g., button, dropdown menu) using a Convolutional Neural Network (CNN), and assembling these components into realistic code. Second, I will present a technique that is capable of translating a screen-recording of a mobile application into a replayable scenario. This technique, called V2S, is based primarily on computer vision techniques and adapts recent solutions for neural object detection and image classification to detect and classify user actions on a screen. Finally, I will conclude my talk by providing a brief overview of related projects, as well as my research vision and planned future work.
  • Tuesday, January 21: Hao Wang (PhD candidate, University of Toronto)
    Title: Optimizing Distributed Machine Learning with Reinforcement Learning
    In the era of Internet of Things, mobile computing and Big Data, millions of sensors and mobile devices are constantly generating massive volumes of data. To utilize the vast amount of data without violating data privacy, Federated Learning has emerged as a new paradigm of distributed machine learning that orchestrates model training across mobile devices. In this talk, I will first introduce the current challenges in distributed machine learning, and then present my recent work on statistical heterogeneity in federated learning, and distributed machine learning on a serverless architecture. Specifically, I will talk about applying reinforcement learning to optimize distributed machine learning by learning the best choice for task scheduling and resource provisioning.
  • Friday, January 24: Xiaowei Jia (PhD candidate, University of Minnesota). The talk will be at 1:00 in CU 401 **Note the room change**
    Title: Physics Guided Machine Learning: A New Paradigm for Scientific Knowledge Discovery
    Data science and machine learning models, which have found tremendous success in several commercial applications where large-scale data is available, e.g., computer vision and natural language processing, has met with limited success in scientific domains. Traditionally, physics-based models of dynamical systems are often used to study engineering and environmental systems. Despite their extensive use, these models have several well-known limitations due to incomplete or inaccurate representations of the physical processes being modeled. Given rapid data growth due to advances in sensor technologies, there is a tremendous opportunity to systematically advance modeling in these domains by using machine learning methods. However, capturing this opportunity is contingent on a paradigm shift in data-intensive scientific discovery since the “black box” use of ML often leads to serious false discoveries in scientific applications.  Because the hypothesis space of scientific applications is often complex and exponentially large, an uninformed data-driven search can easily select a highly complex model that is neither generalizable nor physically interpretable, resulting in the discovery of spurious relationships, predictors, and patterns. This problem becomes worse when there is a scarcity of labeled samples, which is quite common in science and engineering domains.

    My work aims to build the foundations of physics-guided machine learning by exploring several ways of bringing scientific knowledge and machine learning models together. My work has the potential to greatly advance the pace of discovery in a number of scientific and engineering disciplines where physics-based models are used, e.g., hydrology, agriculture, climate science, materials science, power engineering and biomedicine.
  • Tuesday, January 28: Sabirat Rubya (PhD candidate, Computer Science & Engineering Department at University of Minnesota)                                                                                         Title: Facilitating access to peer support through technology for recovery from substance use disorders 
    More than 23 million people in the United States (and a lot more from all over the world) suffer from substance use disorders. Following a crisis medical treatment intervention (e.g., detox and rehab), recovery must be maintained through an ongoing program that includes continued abstinence, peer support, and other mental health interventions. The most common approach to practicing recovery maintenance is by participating in “12-step” programs, such as Alcoholics Anonymous (AA). Most of my work target this crucial phase of the recovery process where people are particularly vulnerable to relapse and where various forms of social support have been found to be particularly helpful. My work combines mixed-methods formative investigations and social computing design techniques (including crowdsourcing, machine learning, and pattern detection) to understand the needs of these recovery communities and create tools to enhance their reach.

    In this talk, I discuss my research that involves working closely with members of recovery communities, understanding what technologies may work for them, and providing implications for research and design in these and other sensitive online contexts. I’ll present my work on (1) investigating peer support and anonymity in online recovery communities, (2) developing new interface technologies to enhance their reach to peer support, and (3) deploying and rigorously evaluating the effectiveness of the developed technologies. I’ll also discuss the application and the effectiveness of human-in-the-loop information retrieval approaches for building technologies in the context of recovery. Finally, I’ll conclude with the implications of my work in a broader domain of mental health, and in designing and implementing technologies that have meaningful impact on health informatics.
  •  Monday, April 27: Dr. Serdar Bozdag (Marquette University) **via Zoom; contact Dr. Michael Zimmer for details**
    Title: Integrating high-dimensional biological datasets to uncover disease-associated genes and gene networks
    With the advances in high-throughput technologies in biology, numerous national and international consortiums have generated a vast amount of genotype, phenotype, gene expression, and epigenetic data, which have been made available to the scientific community. Many of these data, however, have not been analyzed to their full potential and further investigation could provide opportunities to unravel the biological mechanisms behind disease initiation and progression. In my group, we develop machine learning- and network science-based methods to integrate these high dimensional and heterogenous datasets to infer context-specific regulatory interactions and modules, and to predict disease associated genes. In this talk, I will describe two approaches to integrate high dimensional biological datasets. First, I will present our recent tool miRDriver, a statistical machine learning approach to derive copy number-based microRNA-gene interactions in cancer. Second, I will introduce another recent tool PhenoGeneRanker, a novel network propagation-based approach for multiplex heterogenous networks to map genotype to phenotype. We ran PhenoGeneRanker using multi-omics datasets of rice to effectively prioritize the cold tolerance-related genes. At the end of my talk, I will briefly discuss the future trajectory of my research program and some ongoing work.
  • Tuesday, April 28, 1:00pm: Dr. Praveen Madiraju (Marquette University) **via Zoom; contact Dr. Michael Zimmer for details**
    Title: Predicting Post-traumatic Stress Disorder Risk in Veterans
    Veterans form a significant population of the people suffering from post-traumatic stress disorder (PTSD). The National Center for PTSD states that veterans are at an increased risk of developing PTSD compared to the general population with rates of PTSD estimated at 7-8% within the general population and 11-20% among the veteran population. Veterans with PTSD have shown high risk behaviors such as suicide, erratic driving, involvement in interpersonal altercations, substance use disorder (SUD), family discord/dissolution, and social isolation. Hence, predicting PTSD risk earlier will avoid such high-risk behaviors and potentially save lives of veterans.
    I will describe our project iPeer, a comprehensive peer mentoring platform for veterans. The main contributions of the iPeer platform include (i) a 12-week peer mentoring program which includes self-report of PTSD Checklist -5 (PCL-5) and weekly survey questions ,(ii) a fully functional Quick Reaction Force (QRF) App for veterans and mentors, (ii) a grounded theory based approach for identifying complex PTSD related emotional text categories, and (iv) machine learning based approach for identifying early warning signs of PTSD. The project is novel in that there does not exist a comprehensive peer mentoring platform which has all the contributions listed above. In this talk, I will describe in depth the data analysis and evaluation of the machine learning models.

    I will discuss my future research goals which are at the intersection of data science, text analytics and behavioral informatics. I will also present my research, teaching and service goals as they naturally complement the broader industry and community based transformative initiatives in data science.
  • Wednesday, April 29, 1:00pm: Dr. Keke Chen (Wright State University) **via Zoom; contact Dr. Michael Zimmer for details**
    Title: Mining Social Signals to Enhance Privacy Protection and Wisdom of Crowds
    Social signals, such as tweets, posts, blogs, and online discussions, are a significant source of human-generated big data. While appropriately analyzed, they can play an essential role in understanding complex problems such as personal privacy concerns and collective decision-making. In the first part of my talk, I will present our recent work in mining social signals: (1) using tweets to capture the diversity of crowds for achieving the wisdom of crowds, and (2) analyzing deleted tweets to understand users’ privacy concerns and privacy preferences. In the second part of my talk, I will briefly review my research vision and some ongoing and future research projects.
  • Thursday, April 30, 9:30am: Dr. Bill Chen (AIWAYS AUTO) **via Zoom; contact Dr. Michael Zimmer for details**
    Title: Deep Learning for Big Data
    Deep learning is currently an active research area as it has gained huge successes in a broad area of applications such as speech recognition, computer vision etc. With the sheer size of data available today, Big Data brings big opportunities and transformative potential for various sectors;on the other hand, iit also presents unprecedented challenges to harnessing data and information As the data keeps getting bigger, deep learning is coming to play a key role in providing Big Data predictive analytics solutions. In this talk, I will discuss some of our recent research efforts in data variety and noisy labels problems in Big Data. I will also highlight the challenges to Big Data.

Fall 2019

Colloquium dates and speakers for Fall 2019 - Unless specified, the talks will begin at 1:00pm CT in Room 414 at Cudahy Hall.

September 9 - Mike Slattery, Department of Computer Science, Marquette University, "Quantum Computing for Beginners, or, How I Spent My Summer Part I"

September 16 - Mike Slattery, Department of Computer Science, Marquette University. "Quantum Computing for Beginners, or, How I Spent My Summer Part II"

October 7 - Arjun Krishnan, Department of Computational Mathematics, Science and Engineering, Michigan State University, "Hurdles in the marathon of data-driven biology"

October 11 - Blair Taylor, Department of Computer and Information Sciences, Towson University

October 14 - Stevie Chancellor, Department of Computer Science, Northwestern University. "Human-Centered Machine Learning for High-Risk Health Behaviors"

October 21 - Marina Kogan, School of Computing, University of Utah, "Human-Centered Data Science for Crisis Informatics"                  

October 30 - Sameer Patil, School of Informatics, Computing and Engineering, Indiana University, Bloomington, “Mental Models and User Experiences of the Tor Browser”

November 4 - Bilge Mutlu, Department of Computer Sciences, University of Wisconsin Madison, “Designing Robots for Human Interaction”

November 18 - Elena Zheleva, Department of Computer Science, University of Illinois, Chicago, “Causal inference and counterfactual learning from relational data”

November 25 - Mustafa Bilgic, Department of Computer Science, Illinois Institute of Technology, “Active and Interpretable Classification.”


Spring 2019

Colloquium dates and speakers for Spring 2019 - Unless specified, the talks will begin at 2:00pm CT in Room 401 at Cudahy Hall.

Fall 2018

Spring 2018

Fall 2017

Spring 2017