🤖 AI Summary
This paper addresses the evaluation of conjunctive queries (CQs) and, more generally, sum-product queries (SPQs) under strict space constraints—characterizing, for the first time, the fundamental time–space complexity trade-offs. We propose a novel space-efficient algorithmic framework that integrates symbolic computation, dynamic programming, and algebraic circuit optimization. This framework achieves asymptotically reduced space consumption—e.g., from polynomial to logarithmic or even constant space—while retaining near-optimal time complexity. We prove that, for key query classes—including CQs of bounded treewidth and hierarchical SPQs—the framework breaks classical space bottlenecks, enabling efficient evaluation in sublinear and even logarithmic space. Our results establish a rigorous theoretical foundation and provide practical algorithms for resource-constrained settings such as edge computing and embedded database systems.
📝 Abstract
While extensive research on query evaluation has achieved consistent improvements in the time complexity of algorithms, the space complexity of query evaluation has been largely ignored. This is a particular challenge in settings with strict pre-defined space constraints. In this paper, we examine the combined space-time complexity of conjunctive queries (CQs) and, more generally, of sum-product queries (SPQs). We propose several classes of space-efficient algorithms for evaluating SPQs, and we show that the optimal time complexity is almost always achievable with asymptotically lower space complexity than traditional approaches.