Ziad El Sayed
Hi there! I'm pursuing an MSc in Machine Learning at University College London. I recently graduated from NYU Abu Dhabi with a degree in Computer Science and minors in Applied Mathematics and Business Studies. I am particularly interested in the fields of geometric deep learning, information-theoretic approaches to AI fairness, and LLM-based multi-agent systems. I am always striving to leverage my expertise to conduct impactful research and solve complex challenges in these areas.
Selected Projects
Graph Neural Networks for Integrated Circuit Design, Reliability, and Security: Survey and Platform
Graph neural networks (GNNs) have excelled in learning tasks for graph-structured data, including social networks, biology, and circuits. Their success in circuit-related tasks has fueled growing interest in applying GNNs to IC design. This project presents the first comprehensive survey of GNN applications in IC design, covering electronic design automation (EDA), reliability, and security. It introduces a generic GNN application flow—spanning graph conversion, feature extraction, architecture selection, and task formulation—along with GNN4CIRCUITS, a customizable Python tool for researchers. The paper also explores open challenges and future research directions. Under review at ACM Computing Surveys.
Bias Mitigation using Functional Inequalities for Regularization
This work introduces a novel approach to mitigating bias in multimodal machine learning using perturbation and regularization based on functional inequalities. We propose a k-nearest neighbors perturbation method to capture data variability and a refined regularization strategy that distributes the regularization term across multiple hyperparameters for better bias control. To enhance bias assessment, we extend the MMBias dataset with additional target groups, improving demographic representation in cross-modal zero-shot classification. Separately, we evaluate our regularization technique on the Colored MNIST dataset, achieving a 1.4% improvement in generalization accuracy over state-of-the-art methods, reaching 97.65%.
qSa'id: Quantum-ML-Assisted Diagnostic & Treatment Access Platform for Autism
Enhancing Coordination and Decision-Making in LLM-Based Multi-Agent Systems
Enhancing Coordination and Decision-Making in LLM-Based Multi-Agent Systems
The main aim of qSa'id is to cater to the needs of people with autism by providing a quantum approach for early screening and allocating resources efficiently among those who require them. qSai'd involves an efficient hybrid-classical quantum machine learning approach towards improving automated screening, and a parallel solution using QUBO to optimize placements of specialized treatment centers in a health system. Winner of Best Application of Social Good as part of NYUAD's 2022 Hackathon for Social Good.
Enhancing Coordination and Decision-Making in LLM-Based Multi-Agent Systems
Enhancing Coordination and Decision-Making in LLM-Based Multi-Agent Systems
Enhancing Coordination and Decision-Making in LLM-Based Multi-Agent Systems
For my MSc thesis, I will develop coordination mechanisms and adaptive memory for LLM-based multi-agent systems. My research aims to improve decision-making, context retention, and scalability, benchmarking against existing frameworks to enhance multi-agent collaboration.