ETDs

This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.

In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.

Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.

Displaying 1 - 2 of 2
Filtering by

Clear all filters

171809-Thumbnail Image.png

Human-in-the-Loop Machine Learning Systems for Data Integration and Predictive Analytics

Description

Data integration involves the reconciliation of data from diverse data sources in order to obtain a unified data repository, upon which an end user such as a data analyst can run analytics sessions to explore the data and obtain useful insights. Supervised Machine Learning (ML) for data integration tasks such…

Data integration involves the reconciliation of data from diverse data sources in order to obtain a unified data repository, upon which an end user such as a data analyst can run analytics sessions to explore the data and obtain useful insights. Supervised Machine Learning (ML) for data integration tasks such as ontology (schema) or entity (instance) matching requires several training examples in terms of manually curated, pre-labeled matching and non-matching schema concept or entity pairs which are hard to obtain. On similar lines, an analytics system without predictive capabilities about the impending workload can incur huge querying latencies, while leaving the onus of understanding the underlying database schema and writing a meaningful query at every step during a data exploration session on the user. In this dissertation, I will describe the human-in-the-loop Machine Learning (ML) systems that I have built towards data integration and predictive analytics. I alleviate the need for extensive prior labeling by utilizing active learning (AL) for dataintegration. In each AL iteration, I detect the unlabeled entity or schema concept pairs that would strengthen the ML classifier and selectively query the human oracle for such labels in a budgeted fashion. Thus, I make use of human assistance for ML-based data integration. On the other hand, when the human is an end user exploring data through Online Analytical Processing (OLAP) queries, my goal is to pro-actively assist the human by predicting the top-K next queries that s/he is likely to be interested in. I will describe my proposed SQL-predictor, a Business Intelligence (BI) query predictor and a geospatial query cardinality estimator with an emphasis on schema abstraction, query representation and how I adapt the ML models for these tasks. For each system, I will discuss the evaluation metrics and how the proposed systems compare to the state-of-the-art baselines on multiple datasets and query workloads.
ContributorsMeduri, Venkata Vamsikrishna (Author) / Sarwat, Mohamed (Thesis advisor) / Bryan, Chris (Committee member) / Liu, Huan (Committee member) / Ozcan, Fatma (Committee member) / Popa, Lucian (Committee member) / Arizona State University (Publisher)
Created2022
189385-Thumbnail Image.png

Explaining the Vulnerabilities of Machine Learning through Visual Analytics

Description
Machine learning models are increasingly being deployed in real-world applications where their predictions are used to make critical decisions in a variety of domains. The proliferation of such models has led to a burgeoning need to ensure the reliability and safety of these models, given the potential negative consequences of…

Machine learning models are increasingly being deployed in real-world applications where their predictions are used to make critical decisions in a variety of domains. The proliferation of such models has led to a burgeoning need to ensure the reliability and safety of these models, given the potential negative consequences of model vulnerabilities. The complexity of machine learning models, along with the extensive data sets they analyze, can result in unpredictable and unintended outcomes. Model vulnerabilities may manifest due to errors in data input, algorithm design, or model deployment, which can have significant implications for both individuals and society. To prevent such negative outcomes, it is imperative to identify model vulnerabilities at an early stage in the development process. This will aid in guaranteeing the integrity, dependability, and safety of the models, thus mitigating potential risks and enabling the full potential of these technologies to be realized. However, enumerating vulnerabilities can be challenging due to the complexity of the real-world environment. Visual analytics, situated at the intersection of human-computer interaction, computer graphics, and artificial intelligence, offers a promising approach for achieving high interpretability of complex black-box models, thus reducing the cost of obtaining insights into potential vulnerabilities of models. This research is devoted to designing novel visual analytics methods to support the identification and analysis of model vulnerabilities. Specifically, generalizable visual analytics frameworks are instantiated to explore vulnerabilities in machine learning models concerning security (adversarial attacks and data perturbation) and fairness (algorithmic bias). In the end, a visual analytics approach is proposed to enable domain experts to explain and diagnose the model improvement of addressing identified vulnerabilities of machine learning models in a human-in-the-loop fashion. The proposed methods hold the potential to enhance the security and fairness of machine learning models deployed in critical real-world applications.
ContributorsXie, Tiankai (Author) / Maciejewski, Ross (Thesis advisor) / Liu, Huan (Committee member) / Bryan, Chris (Committee member) / Tong, Hanghang (Committee member) / Arizona State University (Publisher)
Created2023