Abdullah Al Mamun
Graduate Student
Joined department: Fall 2017
Education
I am a Ph.D. candidate in the Department of Computer Science at Purdue University, advised by Professor Walid G. Aref. I have also been fortunate to engage in research collaboration with Professor Jianguo Wang and Professor Chunwei Liu. I specialize in Machine Learning for Database Systems, where I build ML-enhanced database system components that are instance-optimized, i.e., custom-tailored to specific data and query workloads. In particular, I develop learned index structures that improve the efficiency of query processing over spatial and vector data. I am also expanding my research toward instance-optimized Database Systems for AI Agents. The systems I envision are tailored to specific AI agents that explore speculative branches through high-frequency forking. These systems aim to process agent-issued queries efficiently while keeping agent-modified data trustworthy.
Selected Publications
Abdullah Al-Mamun, Yeasir Rayhan, and Walid G. Aref. “iFVS: Towards Instance-Optimized Filtered Vector Search.” (arXiv/preprint), 2026.
Abdullah Al-Mamun, Hao Wu, Qiyang He, Jianguo Wang, and Walid G. Aref. “A Survey of Learned Indexes for the Multi-dimensional Space.” ACM Computing Surveys (CSUR), Volume 58, Issue 4, pp. 1-37, 2025.
Abdullah Al-Mamun, Jianguo Wang, and Walid G. Aref. “Learned Indexes From the One-dimensional to the Multi-dimensional Spaces: Challenges, Techniques, and Opportunities.” In Companion of the International Conference on Management of Data (SIGMOD, Tutorial Track), pp. 788-796, 2025.
Abdullah Al-Mamun, Ch. Md. Rakin Haider, and Walid G. Aref. “Query Processing Tradeoffs over an ML-Enhanced R-tree.” In Proceedings of the 8th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (GeoAI@SIGSPATIAL), pp. 174-184, 2025
Abdullah Al-Mamun, Ch. Md. Rakin Haider, Jianguo Wang, and Walid G. Aref. “The “AI+ R”-tree: An Instance-optimized R-tree.” In Proceedings of the 23rd IEEE International Conference on Mobile Data Management (MDM), pp. 9-18. IEEE, 2022.