About Norah Alballa Norah Alballa Ph.D. Student, Computer Science machine learning Federated learning collaborative machine learning knowledge distillation heterogeneous models knowledge transfer LLM multi-model inference Norah Alballa is a Ph.D. student in Computer Science at King Abdullah University of Science and Technology (KAUST), advised by Professor Marco Canini, where her research focuses on collaborative and distributed machine learning, knowledge distillation, federated learning, and efficient inference with large language models. Articles Related News April 2025 A blindfold approach improves machine learning privacy 1 min read · Mon, Apr 28 2025 News Clip News machine learning artificial intelligence distributed systems large-scale computing A query-based method for extracting knowledge from sensitive datasets without showing any underlying private data could resolve long-standing privacy concerns in machine learning.
A blindfold approach improves machine learning privacy 1 min read · Mon, Apr 28 2025 News Clip News machine learning artificial intelligence distributed systems large-scale computing A query-based method for extracting knowledge from sensitive datasets without showing any underlying private data could resolve long-standing privacy concerns in machine learning.
Engage Google Scholar IEEE Xplore ORCID ShareClipboard Related Sites Software-Defined Advanced Networked and Distributed Systems (SANDS) Computer Science (CS) Related Content Articles 1 Events 1 Upcoming Events Improving Collaboration among Heterogeneous Models through Knowledge Transfer and Multi-Model Inference Norah Alballa, Ph.D. Student, Computer Science Nov 22, 17:00 - 19:00 B5 R5220 collaborative machine learning knowledge distillation Federated learning heterogeneous models knowledge transfer LLM multi-model inference
Improving Collaboration among Heterogeneous Models through Knowledge Transfer and Multi-Model Inference Norah Alballa, Ph.D. Student, Computer Science Nov 22, 17:00 - 19:00 B5 R5220 collaborative machine learning knowledge distillation Federated learning heterogeneous models knowledge transfer LLM multi-model inference