Sublinear-Time Algorithms for Counting Star Subgraphs with Applications to Join Selectivity Estimation

TL;DR

This paper introduces sublinear algorithms for estimating sums related to star subgraphs and join selectivity, achieving faster approximation methods by sampling edges directly, surpassing previous vertex-sampling lower bounds.

Contribution

It presents novel sublinear-time algorithms for counting star subgraphs and estimating join selectivity using edge sampling, with tight lower bounds and improved efficiency over prior vertex-based methods.

Findings

Algorithm achieves $(1 \u00b1 \u03b5)$-approximation with query complexity ((m) \, (rac{m \, ext{log log n}}{^2 S_p^{1/p}}))

Provides tight lower bounds for the problem, even with graph structure knowledge

Edge sampling allows surpassing previous lower bounds based on vertex sampling

Abstract

We study the problem of estimating the value of sums of the form $S_p \triangleq \sum \binom{x_i}{p}$ when one has the ability to sample $x_i \geq 0$ with probability proportional to its magnitude. When $p=2$, this problem is equivalent to estimating the selectivity of a self-join query in database systems when one can sample rows randomly. We also study the special case when $\{x_i\}$ is the degree sequence of a graph, which corresponds to counting the number of $p$-stars in a graph when one has the ability to sample edges randomly. Our algorithm for a $(1 \pm \varepsilon)$-multiplicative approximation of $S_p$ has query and time complexities $\O(\frac{m \log \log n}{\epsilon^2 S_p^{1/p}})$. Here, $m=\sum x_i/2$ is the number of edges in the graph, or equivalently, half the number of records in the database table. Similarly, $n$ is the number of vertices in the graph and the number of unique values in the database table. We also provide tight lower bounds (up to polylogarithmic factors) in almost all cases, even when $\{x_i\}$ is a degree sequence and one is allowed to use the structure of the graph to try to get a better estimate. We are not aware of any prior lower bounds on the problem of join selectivity estimation. For the graph problem, prior work which assumed the ability to sample only \emph{vertices} uniformly gave algorithms with matching lower bounds [Gonen, Ron, and Shavitt. \textit{SIAM J. Comput.}, 25 (2011), pp. 1365-1411]. With the ability to sample edges randomly, we show that one can achieve faster algorithms for approximating the number of star subgraphs, bypassing the lower bounds in this prior work. For example, in the regime where $S_p\leq n$, and $p=2$, our upper bound is $\tilde{O}(n/S_p^{1/2})$, in contrast to their $\Omega(n/S_p^{1/3})$ lower bound when no random edge queries are available.