Abdulla Alshabanah

Abdulla Alshabanah

PhD candidate @ University of Southern California

Abdulla Alshabanah

I am a Ph.D. candidate at the University of Southern California (USC) working with Prof. Murali Annavaram. I work on machine learning systems and applied machine learning, with a focus on recommendation systems. I hold a B.S. in Computer Engineering from King Fahd University of Petroleum and Minerals (KFUPM), an M.S. in Computer Engineering, and an M.S. in Computer Science, both from the University of Southern California (USC).

Publication Summary

  • [SIGIR 2026]: A Alshabanah*, C Jiang*, H Zarch, K Balasubramanian and M Annavaram, “HuffmanEmbed: Using Huffman Coding for Embedding Table Compression in Deep Learning Recommendation Models”.
  • [WSDM 2026]: A Alshabanah, Y Yang and M Annavaram, “SAGERec: Sampling and Gating for Enhanced Long-Tail Item Recommendations”. [link]
  • [EMNLP 2025]: A Alshabanah and M Annavaram, “Mind the Dialect: NLP Advancements Uncover Fairness Disparities for Arabic Users in Recommendation Systems”. [link]
  • [ACM Trans. Recomm. Syst. 2025]: A Alshabanah, K Balasubramanian, E Markowitz, G Steeg and M Annavaram, “The Upside of Bias: Personalizing long-tail item recommendations with Biased Sampling” . [link]
  • [RecSys 2025]: A Alshabanah*, C Jiang*, and M Annavaram, “LEAF: Lightweight, Efficient, Adaptive and Flexible Embedding for Large-Scale Recommendation Models”. [link]
  • [PETS 2025]: A Alshabanah, K Balasubramanian and M Annavaram, “Meta-Learn to Unlearn: Enhanced Exact Machine Unlearning in Recommendation Systems with Meta-Learning”. [link]
  • [NAACL 2025]: A Alshabanah and M Annavaram, “On Using Arabic Language Dialects in Recommendation Systems”. [link]
  • [EuroSys 2025 Poster]: A Alshabanah*, C Jiang*, H Zarch, K Balasubramanian and M Annavaram, “HuffmanEmbed: Using Huffman Coding for Embedding Table Compression in Deep Learning Recommendation Models”. [link]
  • [RecSys 2024]: A Alshabanah*, K Balasubramanian*, E Markowitz, G Steeg and M Annavaram, “Biased User History Synthesis for Personalized Long-Tail Item Recommendation”. [link]
  • [RecSys 2024 Workshop]: A Alshabanah*, N Tekle*, A Ayala*, J Haile*, C Baker and M Annavaram, “Music Recommendation through LLM Song Summary”. [link]
  • [RecSys 2024 Workshop]: H Zarch, A Alshabanah, C Jiang and M Annavaram, “CADC: Encoding User-Item Interactions for Compressing Recommendation Model Training Data”.
  • [SPIE 2022]: A Alshabanah, K Balasubramanian, B Krishnamachari, and M Annavaram “Characterizing ML training performance at the tactical edge”. [link]
  • [RecSys 2021]: K Balasubramanian, A Alshabanah, J Choe, and M Annavaram, “cDLRM: Look Ahead Caching for Scalable Training of Recommendation Models”. [link]

* Equal contributions.

Teaching

  • USC EE557 TA: Computer Systems Architecture (Spring 2021, Spring 2023, Fall 2023, Spring 2024 and Spring 2025).
  • USC EE542 TA: Internet and Cloud Computing (Fall 2024).
  • KFUPM COE201 Instructor: Digital Logic Laboratory (Spring 2017).
  • KFUPM COE300 Co-Instructor: Principles of Computer Engineering Design (Fall 2016).

Mentorship

  • USC [CURVE] (Fall 2022 - Present).
  • USC [VSI] (Summer 2022, Summer 2024 and Summer 2025).
  • USC [SHINE] (Summer 2024).