Erwin Dervishai
PhD student at the University of Copenhagen specializing in machine learning and recommender systems, with research on representation learning, disentanglement, and applications of large language models.
Best podcasts with Erwin Dervishai
Ranked by the Snipd community
21 snips
Mar 10, 2026 • 31min
Disentanglement and Interpretability in Recommender Systems
Erwin Dervishai, a PhD student at the University of Copenhagen who studies representation learning and recommender systems. He explores what disentanglement means for learned embeddings. He discusses methods for interpreting embeddings, reproducibility challenges, trade-offs between interpretability and accuracy, using metadata and LLMs for denoising, and practical ideas for user control.
