Research interests
- Recommender systems
- Multimodal and sequential learning
- Fair representation learning
- Optimisation and learning objectives
- Privacy-preserving machine learning
- Robust evaluation under distribution shift
About
Research profile
Bucher Sahyouni is a doctoral researcher in Artificial Intelligence at the University of Surrey, currently in the final thesis write-up stage. His research focuses on architecture and objective design for robust recommendation under sparse implicit feedback.
Current focus
His EPSRC-funded PhD examines how recommender architectures and objectives can extract stronger training signals from sparse, implicit interactions. The work spans multimodal and sequential recommendation, contrastive graph learning, competition-aware softmax objectives, and fairness-aware representation learning.
Research practice
His work covers the full research workflow: literature review, problem formulation, implementation, experimentation, ablation studies, analysis, visualisation, and paper writing. He has also reviewed for SIGIR, AAAI, ICML, ICLR, and RecSys.
Before the PhD, he completed a First-Class MEng in Electronic Engineering with Nanotechnology at the University of Surrey, building a foundation in algorithms, C++, control, communications, and electronic systems.