The classic Yannakakis framework proposed in 1981 is still the state-of-the-art approach for tackling acyclic join-aggregate queries defined over commutative semi-rings. It has been shown that the time complexity of the Yannakakis framework is $O(N + \OUT)$ for any free-connex join-aggregate query, where $N$ is the input size of database and $\OUT$ is the output size of the query result. This is already output-optimal. However, only a general upper bound $O(N \cdot \OUT)$ on the time complexity of the Yannakakis framework is known for the remaining class of acyclic but non-free-connex queries. We first show a lower bound $\Omega\left(N \cdot \OUT^{1- \frac{1}{\outw}} + \OUT\right)$ for computing an acyclic join-aggregate query by {\em semi-ring algorithms}, where $\outw$ is identified as the {\em out-width} of the input query, $N$ is the input size of the database, and $\OUT$ is the output size of the query result. For example, $\outw =2$ for the chain matrix multiplication query, and $\outw=k$ for the star matrix multiplication query with $k$ relations. We give a tighter analysis of the Yannakakis framework and show that Yannakakis framework is already output-optimal on the class of {\em aggregate-hierarchical} queries. However, for the large remaining class of non-aggregate-hierarchical queries, such as chain matrix multiplication query, Yannakakis framework indeed requires $\Theta(N \cdot \OUT)$ time. We next explore a hybrid version of the Yannakakis framework and present an output-optimal algorithm for computing any general acyclic join-aggregate query within $\O\left(N\cdot \OUT^{1-\frac{1}{\outw}} + \OUT\right)$ time, matching the out-width-dependent lower bound up to a poly-logarithmic factor. To the best of our knowledge, this is the first polynomial improvement for computing acyclic join-aggregate queries since 1981.
翻译:暂无翻译