<p>We consider the problem of developing innovative machine learning tools for online education and evaluate their ability to provide instructional resources.  Prediction tasks for student behavior are a complex problem spanning a wide range of topics: we complement current research in student grade prediction and clickstream analysis by considering data from three areas of online learning: Social Learning Networks (SLN), Instructor Feedback, and Learning Management Systems (LMS). In each of these categories, we propose a novel method for modelling data and an associated tool that may be used to assist students and instructors. First, we develop a methodology for analyzing instructor-provided feedback and determining how it correlates with changes in student grades using NLP and NER--based feature extraction. We demonstrate that student grade improvement can be well approximated by a multivariate linear model with average fits across course sections approaching 83\%, and determine several contributors to student success. Additionally, we develop a series of link prediction methodologies that utilize spatial and time-evolving network architectures to pass network state between space and time periods. Through evaluation on six real-world datasets, we find that our method obtains substantial improvements over Bayesian models, linear classifiers, and an unsupervised baseline, with AUCs typically above 0.75 and reaching 0.99. Motivated by Federated Learning, we extend our model of student discussion forums to model an entire classroom as a SLN. We develop a methodology to represent student actions across different course materials in a shared, low-dimensional space that allows characteristics from actions of different types to be passed jointly to a downstream task. Performance comparisons against several baselines in centralized, federated, and personalized learning demonstrate that our model offers more distinctive representations of students in a low-dimensional space, which in turn results in improved accuracy on a common downstream prediction task. Results from these three research thrusts indicate the ability of machine learning methods to accurately model student behavior across multiple data types and suggest their ability to benefit students and instructors alike through future development of assistive tools. </p>

There is a potential in the field of medicine and finance of doing collaborative machine learning. These areas gather data which can be used for developing machine learning models that could predict all from sickness in patients to acts of economical crime like fraud. The problem that exists is that the data collected is mostly of confidential nature and should be handled with precaution. This makes the standard way of doing machine learning - gather data at one centralized server - unwanted to achieve. The safety of the data have to be taken into account. In this project we will explore the Federated learning approach of ”bringing the code to the data, instead of data to the code”. It is a decentralized way of doing machine learning where models are trained on connected devices and data is never shared. Keeping the data privacypreserved.

This thesis explores the training of a deep neural network based named entity recognizer in an end-to-end privacy preserved setting where dataset creation and model training happen in an environment with minimal manual interventions. With the improvement of accuracy in Deep Learning Models for practical tasks, a rising concern is satisfying the demand for training data for these models amidst the concerns on the data privacy. Several scenarios of data protection are suggested in the recent past due to public concerns hence the legal guidelines to enforce them. A promising new development is the decentralized model training on isolated datasets, which eliminates the compromises of privacy upon providing data to a centralized entity. However, in this federated setting curating the data source is still a privacy risk mostly in unstructured data sources such as text. We explore the feasibility of automatic dataset annotation for a Named Entity Recognition (NER) task and training a deep learning model with it in two federated learning settings. We explore the feasibility of utilizing a dataset created in this manner for fine-tuning a stateof- the-art deep learning language model for the downstream task of named entity recognition. We also explore this novel setting of deep learning NLP model and federated learning for its deviation from the classical centralized setting. We created an automatically annotated dataset containing around 80,000 sentences, a manual human annotated test set and tools to extend the dataset with more manual annotations. We observed the noise from automated annotation can be overcome to a level by increasing the dataset size. We also contributed to the federated learning framework with state-of-the-art NLP model developments. Overall, our NER model achieved around 0.80 F1-score for recognition of entities in sentences.

No description available.

No description available.

In recent years, edge computing has become an increasingly popular computing paradigm to enable real-time data processing and mobile intelligence. Edge computing allows computing at the edge of the network, where data is generated and distributed at the nearby edge servers to reduce the data access latency and improve data processing efficiency. In addition, with the advance of Artificial Intelligence of Things (AIoT), not only millions of data are generated from daily smart devices, such as smart light bulbs, smart cameras, and various sensors, but also a large number of parameters of complex machine learning models have to be trained and exchanged by these AIoT devices. Classical cloud-based platforms have difficulty communicating and processing these data/models effectively with sufficient privacy and security protection. Due to the heterogeneity of edge elements including edge servers, mobile users, data resources, and computing tasks, the key challenge is how to effectively manage resources (e.g. data, services) and schedule tasks (e.g. ML/FL tasks) in the edge clouds to meet the QoS of mobile users or maximize the platform's utility. To that end, this dissertation studies joint resource management and task scheduling for mobile edge computing. The key contributions of the dissertation are two-fold. Firstly, we study the data placement problem in edge computing and propose a popularity-based method as well as several load-balancing strategies to effectively place data in the edge network. We further investigate a joint resource placement and task dispatching problem and formulate it as an optimization problem. We propose a two-stage optimization method and a reinforcement learning (RL) method to maximize the total utilities of all tasks. Secondly, we focus on a specific computing task, i.e., federated learning (FL), and study the joint participant selection and learning scheduling problem for multi-model federated edge learning. We formulate a joint optimization problem and propose several multi-stage optimization algorithms to solve the problem. To further improve the FL performance, we leverage the power of the quantum computing (QC) technique and propose a hybrid quantum-classical Benders' decomposition (HQCBD) algorithm as well as a multiple-cuts version to accelerate the convergence speed of the HQCBD algorithm. We show that the proposed algorithms can achieve the consistent optimal value compared with the classical Benders' decomposition running in the classical CPU computer, but with fewer convergence iterations. / Computer and Information Science

The purpose of this dissertation was to explore Board decision making in non-profit sport organizations operating in a multi-level governance system. Four major research objectives were addressed: (1) the way non-profit sport organization Boards make decisions, (2) the types and impacts of non-profit sport organization Boards' internal factors on their decision making, (3) the types and impacts of non-profit sport organization Boards' external factors on their decision making, and (4) the similarities and differences in non-profit sport organization Boards' decision making within and between levels of a federated sport model. Strategic decision-making theory is applied alongside internal (i.e., organization size; organization age; Board structure; Board size; leader-member exchanges; professionalization; socio-demographic indicators; motivation; and skills, expertise, and experience) and external factors (i.e., legal requirements, institutional pressures, inter-organizational relationships, market conditions, collaboration, stakeholders, and federated sport model) - originating from the Integrated Board Performance Model and relevant sport governance literature - to comprise the dissertation's theoretical framework. A multiple case study methodology was used featuring six non-profit sport organizations Boards (two national and four provincial/territorial) operating in the Canadian sport system. Data were collected longitudinally through three methods: non-participant overt observations, semi-structured interviews, and documents. Data were thematically analyzed via NVivo12, and SPSS was used for descriptive statistics and comparisons of the observed Board decisions (i.e., t-tests, ANOVA). Board decision making in non-profit sport organizations was identified as information and engagement based, which incorporated multiple sources of internal and external information, involved five members, and occurred over two meetings with some informal interactions (e.g., email discussions between Board members). Five internal factors impacted Board decision making: Board composition, Board size, Chair-Chief Executive Officer relationship, Board meeting practices and environment, and technology. The first four had a positive impact, while the latter resulted in both a positive and negative impact on Board decision making. Two external factors had a negative impact on Board decision making: the sport system structure and market conditions. Seven statistically significant differences were identified in Board decision making at the provincial/territorial level (none for national non-profit sport organizations) and 21 between levels (i.e., national versus provincial/territorial) of the federated sport model. More similarities than differences were found when comparing Board decision making within (i.e., two non-profit sport organizations at the national level, four non-profit sport organizations at the provincial/territorial level) and between (i.e., national versus provincial/territorial non-profit sport organizations) levels of a federated sport model, notably related to duration and interactions. However, differences were attributed to sources of delays, the process to acquire information, and the types of information sources used. Overall, non-profit sport organizations Boards' decision making in a federated sport model is characterized with complexities arising from internal and external factors, thereby having a positive or negative impact on duration, delays, interactions, process to acquire information, and types of information sources used to make decisions. These notions are illustrated in the developed Non-Profit Sport Organization Board Decision Making Model, which address the dissertation's overall purpose. Altogether, this dissertation offers theoretical and practical contributions. Notably, it demonstrated strategic decision-making theory's temporal and contextual boundary to investigate the chosen phenomenon at the group level (i.e., Boards) of non-profit sport organizations in a federated sport model. Further, the conceptual rigour of the applied theory is developed as novel variables (e.g., technology) to measure sub-constructs (e.g., impediments) identified in this dissertation should be incorporated to better understand decision making. Results also contribute to the broader sport governance literature as the approach undertaken in this dissertation supports the value and need for multi-method, in situ, and longitudinal research designs to better understand process-based phenomena (e.g., Board decision making). Practically, this dissertation's results develop strategies and recommendations for Boards of non-profit sport organizations. Specifically, Boards should understand virtual meetings are convenient, cost-friendly, and allow decisions to be made even when restrictions are imposed during a health crisis (e.g., travel, social). However, delays and challenges in engagement are found during virtual meetings. To engage members during decision making, Chairs have an important role to ensure a diverse set of perspectives are gathered from individual members, thereby making a better informed decision. Formalizing decision making with purposefully developed documents (e.g., Board papers) and an action registry is also vital for Boards to be transparent and accountable in their decisions made.

Federated learning is a framework in machine learning that allows for training a model while maintaining data privacy. Moreover, it allows clients with their own data to collaborate in order to build a stronger, shared model. Federated learning is of particular interest to healthcare data, since it is of the utmost importance to respect patient privacy while still building useful diagnostic tools. However, healthcare data can be complicated — data format might differ across providers, leading to unexpected inputs and incompatibility between different providers. For example, electrocardiograms might differ in sampling rate or number of leads used, meaning that a classifier trained at one hospital might be useless to another. We propose using autoencoders to address this problem, transforming important information contained in electrocardiograms to a uniform input, where federated learning can then be used to train a strong classifier for multiple healthcare providers. Furthermore, we propose using statistically-guided hyperparameter tuning to ensure fast convergence of the model.

<p><br></p><p>How to set privacy parameters is a crucial problem for the consistent application of DP in practice. The current privacy parameters do not provide direct suggestions for this problem. On the other hand, different databases may have varying degrees of information leakage, allowing attackers to enhance their attacks with the available information. This dissertation provides an additional interpretation of the current DP notions by introducing a framework that directly considers the worst-case average failure probability of attackers under different levels of knowledge. </p><p><br></p><p>To achieve this, we introduce a novel measure of attacker knowledge and establish a dual relationship between (type I error, type II error) and (prior, average failure probability). By leveraging this framework, we propose an interpretable paradigm to consistently set privacy parameters on different databases with varying levels of leaked information. </p><p><br></p><p>Furthermore, we characterize the minimax limit of private parameter estimation, driven by $1/(n(1-2p))^2+1/n$, where $p$ represents the worst-case probability risk and $n$ is the number of data points. This characterization is more interpretable than the current lower bound $\min{1/(n\epsilon^2),1/(n\delta^2)}+1/n$ on $(\epsilon,\delta)$-DP. Additionally, we identify the phase transition of private parameter estimation based on this limit and provide suggestions for protocol designs to achieve optimal private estimations. </p><p><br></p><p>Last, we consider a federated learning setting where the data are stored in a distributed manner and privacy-preserving interactions are required. We extend the proposed interpretation to federated learning, considering two scenarios: protecting against privacy breaches against local nodes and protecting privacy breaches against the center. Specifically, we consider a non-convex sparse federated parameter estimation problem and apply it to the generalized linear models. We tackle two challenges in this setting. Firstly, we encounter the issue of initialization due to the privacy requirements that limit the number of queries to the database. Secondly, we overcome the heterogeneity in the distribution among local nodes to identify low-dimensional structures.</p>

<p>  </p> <p>Federated learning (FL) has emerged as a promising approach for training machine learning models on distributed data while ensuring privacy preservation and data locality. However, one key challenge in FL optimization is the lack of high probability guarantees, which can undermine the trustworthiness of FL solutions. To address this critical issue, we introduce Federated Averaging with post-optimization (FedAvg-PO) method, a modification to the Federated Averaging (FedAvg) algorithm. The proposed algorithm applies a post-optimization phase to evaluate a short list of solutions generated by several independent runs of the FedAvg method. These modifications allow to significantly improve the large-deviation properties of FedAvg which improve the reliability and robustness of the optimization process. The novel complexity analysis shows that FedAvg-PO can compute accurate and statistically guaranteed solutions in the federated learning context. Our result further relaxes the restrictive assumptions in FL theory by developing new technical tools which may be of independent interest. The insights provided by the computational requirements analysis contribute to the understanding of the scalability and efficiency of the algorithm, guiding its practical implementation.</p>