Searcharxiv⌕ Search

arXiv subjects

Mohammad Khalil

Publications and source records attributed to Mohammad Khalil.

At least 19 recordsLinked to original sources
arXiv2026

Fed-CausalDiff: Decoupled Synchronization for Federated Do-Simulation and Policy Evaluation

While federated learning enables collaborative modelling on decentralised data, standard methods merely fit historical observations. This purely observational approach is fundamentally insufficient for interventional inference and policy evaluation, as sequential actions dynamically alter future states. We propose \textbf{Fed-CausalDiff}, a federated causal diffusion framework for do-simulation. The architecture decomposes the evolution of the latent state into a global causal score function and a local confounding score function. This design enables \emph{decoupled synchronisation} (DSS), where clients aggregate only the shared causal mechanism while retaining site-specific confounders locally to handle heterogeneity. Experiments on four datasets demonstrate that Fed-CausalDiff achieves better ATE and policy-value estimation accuracy, offering a favorable trade-off between communication cost and inference fidelity.

cs.LG↗
arXiv2026

Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN

Foundation models for tabular data, such as the Tabular Prior-data Fitted Network (TabPFN), are pre-trained on a massive number of synthetic datasets generated by structural causal models (SCM). They leverage in-context learning to offer high predictive accuracy in real-world tasks. However, the fairness properties of these foundational models, which incorporate ideas from causal reasoning during pre-training, remain underexplored. In this work, we conduct a comprehensive empirical evaluation of TabPFN and its fine-tuned variants, assessing predictive performance, fairness, and robustness across varying dataset sizes and distributional shifts. Our results reveal that while TabPFN achieves stronger predictive accuracy compared to baselines and exhibits robustness to spurious correlations, improvements in fairness are moderate and inconsistent, particularly under missing-not-at-random (MNAR) covariate shifts. These findings suggest that the causal pre-training in TabPFN is helpful but insufficient for algorithmic fairness, highlighting implications for deploying TabPFN (and similar) models in practice and the need for further fairness interventions.

cs.LG↗
arXiv2026

Brief but Impactful: How Human Tutoring Interactions Shape Engagement in Online Learning

Learning analytics can guide human tutors to efficiently address motivational barriers to learning that AI systems struggle to support. Students become more engaged when they receive human attention. However, what occurs during short interventions, and when are they most effective? We align student-tutor dialogue transcripts with MATHia tutoring system log data to study brief human-tutor interactions on Zoom drawn from 2,075 hours of 191 middle school students' classroom math practice. Mixed-effect models reveal that engagement, measured as successful solution steps per minute, is higher during a human-tutor visit and remains elevated afterward. Visit length exhibits diminishing returns: engagement rises during and shortly after visits, irrespective of visit length. Timing also matters: later visits yield larger immediate lifts than earlier ones, though an early visit remains important to counteract engagement decline. We create analytics that identify which tutor-student dialogues raise engagement the most. Qualitative analysis reveals that interactions with concrete, stepwise scaffolding with explicit work organization elevate engagement most strongly. We discuss implications for resource-constrained tutoring, prioritizing several brief, well-timed check-ins by a human tutor while ensuring at least one early contact. Our analytics can guide the prioritization of students for support and surface effective tutor moves in real-time.

cs.CY↗
arXiv2026

Quality Degradation Attack in Synthetic Data

Synthetic Data Generation (SDG) can be used to facilitate privacy-preserving data sharing. However, most existing research focuses on privacy attacks where the adversary is the recipient of the released synthetic data and attempts to infer sensitive information from it. This study investigates quality degradation attacks initiated by adversaries who possess access to the real dataset or control over the generation process, such as the data owner, the synthetic data provider, or potential intruders. We formalize a corresponding threat model and empirically evaluate the effectiveness of targeted manipulations of real data (e.g., label flipping and feature-importance-based interventions) on the quality of generated synthetic data. The results show that even small perturbations can substantially reduce downstream predictive performance and increase statistical divergence, exposing vulnerabilities within SDG pipelines. This study highlights the need to integrate integrity verification and robustness mechanisms, alongside privacy protection, to ensure the reliability and trustworthiness of synthetic data sharing frameworks.

cs.CR↗
arXiv2025

Measuring the Impact of Student Gaming Behaviors on Learner Modeling

The expansion of large-scale online education platforms has made vast amounts of student interaction data available for knowledge tracing (KT). KT models estimate students' concept mastery from interaction data, but their performance is sensitive to input data quality. Gaming behaviors, such as excessive hint use, may misrepresent students' knowledge and undermine model reliability. However, systematic investigations of how different types of gaming behaviors affect KT remain scarce, and existing studies rely on costly manual analysis that does not capture behavioral diversity. In this study, we conceptualize gaming behaviors as a form of data poisoning, defined as the deliberate submission of incorrect or misleading interaction data to corrupt a model's learning process. We design Data Poisoning Attacks (DPAs) to simulate diverse gaming patterns and systematically evaluate their impact on KT model performance. Moreover, drawing on advances in DPA detection, we explore unsupervised approaches to enhance the generalizability of gaming behavior detection. We find that KT models' performance tends to decrease especially in response to random guess behaviors. Our findings provide insights into the vulnerabilities of KT models and highlight the potential of adversarial methods for improving the robustness of learning analytics systems.

cs.CY↗
arXiv2025

Closure Term Estimation in Spatiotemporal Models of Dynamical Systems

Closure modeling - the statistical modeling of missing dynamics in the natural sciences and engineering - is a growing and active area of research. Existing methods for closure modeling are often computationally prohibitive, lack uncertainty quantification, or require noise-free observations of the temporal derivatives over the system state. We propose a novel, computationally efficient approach for the modeling and estimation of closure terms over the spatiotemporal domain that provides uncertainty quantification and is effective even when the observations of the system state are sparse or contain moderate levels of noise. The efficacy of our approach is demonstrated in both one and two spatial dimensions through numerical experiments using the Fisher-KPP reaction-diffusion equation and the advection-diffusion equation as exemplars.

stat.ME↗
arXiv2025

A Showdown of ChatGPT vs DeepSeek in Solving Programming Tasks

The advancement of large language models (LLMs) has created a competitive landscape for AI-assisted programming tools. This study evaluates two leading models: ChatGPT 03-mini and DeepSeek-R1 on their ability to solve competitive programming tasks from Codeforces. Using 29 programming tasks of three levels of easy, medium, and hard difficulty, we assessed the outcome of both models by their accepted solutions, memory efficiency, and runtime performance. Our results indicate that while both models perform similarly on easy tasks, ChatGPT outperforms DeepSeek-R1 on medium-difficulty tasks, achieving a 54.5% success rate compared to DeepSeek 18.1%. Both models struggled with hard tasks, thus highlighting some ongoing challenges LLMs face in handling highly complex programming problems. These findings highlight key differences in both model capabilities and their computational power, offering valuable insights for developers and researchers working to advance AI-driven programming tools.

cs.SE↗
arXiv2025

Towards Privacy-Preserving Data-Driven Education: The Potential of Federated Learning

The increasing adoption of data-driven applications in education such as in learning analytics and AI in education has raised significant privacy and data protection concerns. While these challenges have been widely discussed in previous works, there are still limited practical solutions. Federated learning has recently been discoursed as a promising privacy-preserving technique, yet its application in education remains scarce. This paper presents an experimental evaluation of federated learning for educational data prediction, comparing its performance to traditional non-federated approaches. Our findings indicate that federated learning achieves comparable predictive accuracy. Furthermore, under adversarial attacks, federated learning demonstrates greater resilience compared to non-federated settings. We summarise that our results reinforce the value of federated learning as a potential approach for balancing predictive performance and privacy in educational contexts.

cs.LG↗
arXiv2025

Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms

The increasing use of machine learning in learning analytics (LA) has raised significant concerns around algorithmic fairness and privacy. Synthetic data has emerged as a dual-purpose tool, enhancing privacy and improving fairness in LA models. However, prior research suggests an inverse relationship between fairness and privacy, making it challenging to optimize both. This study investigates which synthetic data generators can best balance privacy and fairness, and whether pre-processing fairness algorithms, typically applied to real datasets, are effective on synthetic data. Our results highlight that the DEbiasing CAusal Fairness (DECAF) algorithm achieves the best balance between privacy and fairness. However, DECAF suffers in utility, as reflected in its predictive accuracy. Notably, we found that applying pre-processing fairness algorithms to synthetic data improves fairness even more than when applied to real data. These findings suggest that combining synthetic data generation with fairness pre-processing offers a promising approach to creating fairer LA models.

cs.LG↗
arXiv2025

Creating Artificial Students that Never Existed: Leveraging Large Language Models and CTGANs for Synthetic Data Generation

In this study, we explore the growing potential of AI and deep learning technologies, particularly Generative Adversarial Networks (GANs) and Large Language Models (LLMs), for generating synthetic tabular data. Access to quality students data is critical for advancing learning analytics, but privacy concerns and stricter data protection regulations worldwide limit their availability and usage. Synthetic data offers a promising alternative. We investigate whether synthetic data can be leveraged to create artificial students for serving learning analytics models. Using the popular GAN model CTGAN and three LLMs- GPT2, DistilGPT2, and DialoGPT, we generate synthetic tabular student data. Our results demonstrate the strong potential of these methods to produce high-quality synthetic datasets that resemble real students data. To validate our findings, we apply a comprehensive set of utility evaluation metrics to assess the statistical and predictive performance of the synthetic data and compare the different generator models used, specially the performance of LLMs. Our study aims to provide the learning analytics community with valuable insights into the use of synthetic data, laying the groundwork for expanding the field methodological toolbox with new innovative approaches for learning analytics data generation.

cs.LG↗
arXiv2025

Advancing privacy in learning analytics using differential privacy

This paper addresses the challenge of balancing learner data privacy with the use of data in learning analytics (LA) by proposing a novel framework by applying Differential Privacy (DP). The need for more robust privacy protection keeps increasing, driven by evolving legal regulations and heightened privacy concerns, as well as traditional anonymization methods being insufficient for the complexities of educational data. To address this, we introduce the first DP framework specifically designed for LA and provide practical guidance for its implementation. We demonstrate the use of this framework through a LA usage scenario and validate DP in safeguarding data privacy against potential attacks through an experiment on a well-known LA dataset. Additionally, we explore the trade-offs between data privacy and utility across various DP settings. Our work contributes to the field of LA by offering a practical DP framework that can support researchers and practitioners in adopting DP in their works.

cs.CR↗
arXiv2024

Probabilistic transfer learning methodology to expedite high fidelity simulation of reactive flows

Reduced order models based on the transport of a lower dimensional manifold representation of the thermochemical state, such as Principal Component (PC) transport and Machine Learning (ML) techniques, have been developed to reduce the computational cost associated with the Direct Numerical Simulations (DNS) of reactive flows. Both PC transport and ML normally require an abundance of data to exhibit sufficient predictive accuracy, which might not be available due to the prohibitive cost of DNS or experimental data acquisition. To alleviate such difficulties, similar data from an existing dataset or domain (source domain) can be used to train ML models, potentially resulting in adequate predictions in the domain of interest (target domain). This study presents a novel probabilistic transfer learning (TL) framework to enhance the trust in ML models in correctly predicting the thermochemical state in a lower dimensional manifold and a sparse data setting. The framework uses Bayesian neural networks, and autoencoders, to reduce the dimensionality of the state space and diffuse the knowledge from the source to the target domain. The new framework is applied to one-dimensional freely-propagating flame solutions under different data sparsity scenarios. The results reveal that there is an optimal amount of knowledge to be transferred, which depends on the amount of data available in the target domain and the similarity between the domains. TL can reduce the reconstruction error by one order of magnitude for cases with large sparsity. The new framework required 10 times less data for the target domain to reproduce the same error as in the abundant data scenario. Furthermore, comparisons with a state-of-the-art deterministic TL strategy show that the probabilistic method can require four times less data to achieve the same reconstruction error.

physics.chem-ph↗
arXiv2024

Scaling While Privacy Preserving: A Comprehensive Synthetic Tabular Data Generation and Evaluation in Learning Analytics

Privacy poses a significant obstacle to the progress of learning analytics (LA), presenting challenges like inadequate anonymization and data misuse that current solutions struggle to address. Synthetic data emerges as a potential remedy, offering robust privacy protection. However, prior LA research on synthetic data lacks thorough evaluation, essential for assessing the delicate balance between privacy and data utility. Synthetic data must not only enhance privacy but also remain practical for data analytics. Moreover, diverse LA scenarios come with varying privacy and utility needs, making the selection of an appropriate synthetic data approach a pressing challenge. To address these gaps, we propose a comprehensive evaluation of synthetic data, which encompasses three dimensions of synthetic data quality, namely resemblance, utility, and privacy. We apply this evaluation to three distinct LA datasets, using three different synthetic data generation methods. Our results show that synthetic data can maintain similar utility (i.e., predictive performance) as real data, while preserving privacy. Furthermore, considering different privacy and data utility requirements in different LA scenarios, we make customized recommendations for synthetic data generation. This paper not only presents a comprehensive evaluation of synthetic data but also illustrates its potential in mitigating privacy concerns within the field of LA, thus contributing to a wider application of synthetic data in LA and promoting a better practice for open science.

cs.CR↗
arXiv2023

Have Learning Analytics Dashboards Lived Up to the Hype? A Systematic Review of Impact on Students' Achievement, Motivation, Participation and Attitude

While learning analytics dashboards (LADs) are the most common form of LA intervention, there is limited evidence regarding their impact on students learning outcomes. This systematic review synthesizes the findings of 38 research studies to investigate the impact of LADs on students' learning outcomes, encompassing achievement, participation, motivation, and attitudes. As we currently stand, there is no evidence to support the conclusion that LADs have lived up to the promise of improving academic achievement. Most studies reported negligible or small effects, with limited evidence from well-powered controlled experiments. Many studies merely compared users and non-users of LADs, confounding the dashboard effect with student engagement levels. Similarly, the impact of LADs on motivation and attitudes appeared modest, with only a few exceptions demonstrating significant effects. Small sample sizes in these studies highlight the need for larger-scale investigations to validate these findings. Notably, LADs showed a relatively substantial impact on student participation. Several studies reported medium to large effect sizes, suggesting that LADs can promote engagement and interaction in online learning environments. However, methodological shortcomings, such as reliance on traditional evaluation methods, self-selection bias, the assumption that access equates to usage, and a lack of standardized assessment tools, emerged as recurring issues. To advance the research line for LADs, researchers should use rigorous assessment methods and establish clear standards for evaluating learning constructs. Such efforts will advance our understanding of the potential of LADs to enhance learning outcomes and provide valuable insights for educators and researchers alike.

cs.HC↗
arXiv2023

Enhancing Polynomial Chaos Expansion Based Surrogate Modeling using a Novel Probabilistic Transfer Learning Strategy

In the field of surrogate modeling, polynomial chaos expansion (PCE) allows practitioners to construct inexpensive yet accurate surrogates to be used in place of the expensive forward model simulations. For black-box simulations, non-intrusive PCE allows the construction of these surrogates using a set of simulation response evaluations. In this context, the PCE coefficients can be obtained using linear regression, which is also known as point collocation or stochastic response surfaces. Regression exhibits better scalability and can handle noisy function evaluations in contrast to other non-intrusive approaches, such as projection. However, since over-sampling is generally advisable for the linear regression approach, the simulation requirements become prohibitive for expensive forward models. We propose to leverage transfer learning whereby knowledge gained through similar PCE surrogate construction tasks (source domains) is transferred to a new surrogate-construction task (target domain) which has a limited number of forward model simulations (training data). The proposed transfer learning strategy determines how much, if any, information to transfer using new techniques inspired by Bayesian modeling and data assimilation. The strategy is scrutinized using numerical investigations and applied to an engineering problem from the oil and gas industry.

stat.ML↗
arXiv2023

Transfer learning for predicting source terms of principal component transport in chemically reactive flow

The objective of this study is to evaluate whether the number of requisite training samples can be reduced with the use of various transfer learning models for predicting, for example, the chemical source terms of the data-driven reduced-order model that represents the homogeneous ignition process of a hydrogen/air mixture. Principal component analysis is applied to reduce the dimensionality of the hydrogen/air mixture in composition space. Artificial neural networks (ANNs) are used to tabulate the reaction rates of principal components, and subsequently, a system of ordinary differential equations is solved. As the number of training samples decreases at the target task (i.e.,for T0 > 1000 K and various phi), the reduced-order model fails to predict the ignition evolution of a hydrogen/air mixture. Three transfer learning strategies are then applied to the training of the ANN model with a sparse dataset. The performance of the reduced-order model with a sparse dataset is found to be remarkably enhanced if the training of the ANN model is restricted by a regularization term that controls the degree of knowledge transfer from source to target tasks. To this end, a novel transfer learning method is introduced, parameter control via partial initialization and regularization (PaPIR), whereby the amount of knowledge transferred is systemically adjusted for the initialization and regularization of the ANN model in the target task. It is found that an additional performance gain can be achieved by changing the initialization scheme of the ANN model in the target task when the task similarity between source and target tasks is relatively low.

physics.chem-ph↗
arXiv2023

Sparse Bayesian neural networks for regression: Tackling overfitting and computational challenges in uncertainty quantification

Neural networks (NNs) are primarily developed within the frequentist statistical framework. Nevertheless, frequentist NNs lack the capability to provide uncertainties in the predictions, and hence their robustness can not be adequately assessed. Conversely, the Bayesian neural networks (BNNs) naturally offer predictive uncertainty by applying Bayes' theorem. However, their computational requirements pose significant challenges. Moreover, both frequentist NNs and BNNs suffer from overfitting issues when dealing with noisy and sparse data, which render their predictions unwieldy away from the available data space. To address both these problems simultaneously, we leverage insights from a hierarchical setting in which the parameter priors are conditional on hyperparameters to construct a BNN by applying a semi-analytical framework known as nonlinear sparse Bayesian learning (NSBL). We call our network sparse Bayesian neural network (SBNN) which aims to address the practical and computational issues associated with BNNs. Simultaneously, imposing a sparsity-inducing prior encourages the automatic pruning of redundant parameters based on the automatic relevance determination (ARD) concept. This process involves removing redundant parameters by optimally selecting the precision of the parameters prior probability density functions (pdfs), resulting in a tractable treatment for overfitting. To demonstrate the benefits of the SBNN algorithm, the study presents an illustrative regression problem and compares the results of a BNN using standard Bayesian inference, hierarchical Bayesian inference, and a BNN equipped with the proposed algorithm. Subsequently, we demonstrate the importance of considering the full parameter posterior by comparing the results with those obtained using the Laplace approximation with and without NSBL.

cs.CE↗
arXiv2023

A Bayesian model calibration framework for stochastic compartmental models with both time-varying and time-invariant parameters

We consider state and parameter estimation for compartmental models having both time-varying and time-invariant parameters. Though the described Bayesian computational framework is general, we look at a specific application to the susceptible-infectious-removed (SIR) model which describes a basic mechanism for the spread of infectious diseases through a system of coupled nonlinear differential equations. The SIR model consists of three states, namely, the three compartments, and two parameters which control the coupling among the states. The deterministic SIR model with time-invariant parameters has shown to be overly simplistic for modelling the complex long-term dynamics of diseases transmission. Recognizing that certain model parameters will naturally vary in time due to seasonal trends, non-pharmaceutical interventions, and other random effects, the estimation procedure must systematically permit these time-varying effects to be captured, without unduly introducing artificial dynamics into the system. To this end, we leverage the robustness of the Markov Chain Monte Carlo (MCMC) algorithm for the estimation of time-invariant parameters alongside nonlinear filters for the joint estimation of the system state and time-varying parameters. We demonstrate performance of the framework by first considering a series of examples using synthetic data, followed by an exposition on public health data collected in the province of Ontario.

cs.CE↗