Amine (أمين) Mhedhbi

selected publications

1. ACM TODS

   Optimizing One-time and Continuous Subgraph Queries using Worst-case Optimal Joins

   Amine Mhedhbi, Chathura Kankanamge, and Semih Salihoglu

   ACM Transactions on Database Systems (TODS), 2021

   Abs HTML PDF

   We study the problem of optimizing one-time and continuous subgraph queries using the new worst-case optimal join plans. Worst-case optimal plans evaluate queries by matching one query vertex at a time using multiway intersections. The core problem in optimizing worst-case optimal plans is to pick an ordering of the query vertices to match. We make two main contributions:

   1. A cost-based dynamic programming optimizer for one-time queries that (i) picks efficient query vertex orderings for worst-case optimal plans and (ii) generates hybrid plans that mix traditional binary joins with worst-case optimal style multiway intersections. In addition to our optimizer, we describe an adaptive technique that changes the query vertex orderings of the worst-case optimal subplans during query execution for more efficient query evaluation. The plan space of our one-time optimizer contains plans that are not in the plan spaces based on tree decompositions from prior work.

   2. A cost-based greedy optimizer for continuous queries that builds on the delta subgraph query framework. Given a set of continuous queries, our optimizer decomposes these queries into multiple delta subgraph queries, picks a plan for each delta query, and generates a single combined plan that evaluates all of the queries. Our combined plans share computations across operators of the plans for the delta queries if the operators perform the same intersections. To increase the amount of computation shared, we describe an additional optimization that shares partial intersections across operators.

   Our optimizers use a new cost metric for worst-case optimal plans called intersection-cost. When generating hybrid plans, our dynamic programming optimizer for one-time queries combines intersection-cost with the cost of binary joins. We demonstrate the effectiveness of our plans, adaptive technique, and partial intersection sharing optimization through extensive experiments. Our optimizers are integrated into GraphflowDB.

   Proc. VLDB

   Columnar Storage and List-based Processing for Graph Database Management Systems

   Pranjal Gupta, Amine Mhedhbi, and Semih Salihoglu

   Proceedings of the VLDB Endowment, 2021

   Abs HTML PDF

   We revisit column-oriented storage and query processing techniques in the context of contemporary graph database management systems (GDBMSs). Similar to column-oriented RDBMSs, GDBMSs support read-heavy analytical workloads that however have fundamentally different data access patterns than traditional analytical workloads. We first derive a set of desiderata for optimizing storage and query processors of GDBMS based on their access patterns. We then present the design of columnar storage, compression, and query processing techniques based on these desiderata. In addition to showing direct integration of existing techniques from columnar RDBMSs, we also propose novel ones that are optimized for GDBMSs. These include a novel list-based query processor, which avoids expensive data copies of traditional block-based processors under many-to-many joins and avoids materializing adjacency lists in intermediate tuples, a new data structure we call single-indexed edge property pages and an accompanying edge ID scheme, and a new application of Jacobson's bit vector index for compressing NULL values and empty lists. We integrated our techniques into the GraphflowDB in-memory GDBMS. Through extensive experiments, we demonstrate the scalability and query performance benefits of our techniques.