arXiv subjects

Jinchao Huang

Publications and source records attributed to Jinchao Huang.

6 recordsLinked to original sources

arXiv2026

Towards Output-Optimal Uniform Sampling and Approximate Counting for Join-Project Queries

Uniform sampling and approximate counting are fundamental primitives for modern database applications, ranging from query optimization to approximate query processing. While recent breakthroughs have established optimal sampling and counting algorithms for full join queries, a significant gap remains for join-project queries, which are ubiquitous in real-world workloads. The state-of-the-art ``propose-and-verify'' framework \cite{chen2020random} for these queries suffers from fundamental inefficiencies, often yielding prohibitive complexity when projections significantly reduce the output size. In this paper, we present the first asymptotically optimal algorithms for fundamental classes of join-project queries, including matrix, star, and chain queries. By leveraging a novel rejection-based sampling strategy and a hybrid counting reduction, we achieve polynomial speedups over the state of the art. We establish the optimality of our results through matching communication complexity lower bounds, which hold even against algebraic techniques like fast matrix multiplication. Finally, we delineate the theoretical limits of the problem space. While matrix and star queries admit efficient sublinear-time algorithms, we establish a significantly stronger lower bound for chain queries, demonstrating that sublinear algorithms are impossible in general.

cs.DB↗

arXiv2025

Subset Sampling over Joins

Subset sampling (also known as Poisson sampling), where the decision to include any specific element in the sample is made independently of all others, is a fundamental primitive in data analytics, enabling efficient approximation by processing representative subsets rather than massive datasets. While sampling from explicit lists is well-understood, modern applications -- such as machine learning over relational data -- often require sampling from a set defined implicitly by a relational join. In this paper, we study the problem of \emph{subset sampling over joins}: drawing a random subset from the join results, where each join result is included independently with some probability. We address the general setting where the probability is derived from input tuple weights via decomposable functions (e.g., product, sum, min, max). Since the join size can be exponentially larger than the input, the naive approach of materializing all join results to perform subset sampling is computationally infeasible. We propose the first efficient algorithms for subset sampling over acyclic joins: (1) a \emph{static index} for generating multiple (independent) subset samples over joins; (2) a \emph{one-shot} algorithm for generating a single subset sample over joins; (3) a \emph{dynamic index} that can support tuple insertions, while maintaining a one-shot sample or generating multiple (independent) samples. Our techniques achieve near-optimal time and space complexity with respect to the input size and the expected sample size.

cs.DB↗

arXiv2024

DIPS: Optimal Dynamic Index for Poisson $\boldsymbolπ$ps Sampling

This paper addresses the Poisson $π$ps sampling problem, a topic of significant academic interest in various domains and with practical data mining applications, such as influence maximization. The problem includes a set $\mathcal{S}$ of $n$ elements, where each element $v$ is assigned a weight $w(v)$ reflecting its importance. The goal is to generate a random subset $X$ of $\mathcal{S}$, where each element $v \in \mathcal{S}$ is included in $X$ independently with probability $\frac{c\cdot w(v)}{\sum_{v \in \mathcal{S}} w(v)}$, where $0<c\leq 1$ is a constant. The subsets must be independent across different queries. While the Poisson $π$ps sampling problem can be reduced to the well-studied subset sampling problem, updates in Poisson $π$ps sampling, such as adding a new element or removing an element, would cause the probabilities of all $n$ elements to change in the corresponding subset sampling problem, making this approach impractical for dynamic scenarios. To address this, we propose a dynamic index specifically tailored for the Poisson $π$ps sampling problem, supporting optimal expected $\mathcal{O}(1)$ query time and $\mathcal{O}(1)$ index update time, with an optimal $\mathcal{O}(n)$ space cost. Our solution involves recursively partitioning the set by weights and ultimately using table lookup. The core of our solution lies in addressing the challenges posed by weight explosion and correlations between elements. Empirical evaluations demonstrate that our approach achieves significant speedups in update time while maintaining consistently competitive query time compared to the subset-sampling-based methods.

cs.DB↗

arXiv2023

Subset Sampling and Its Extensions

This paper studies the \emph{subset sampling} problem. The input is a set $\mathcal{S}$ of $n$ records together with a function $\textbf{p}$ that assigns each record $v\in\mathcal{S}$ a probability $\textbf{p}(v)$. A query returns a random subset $X$ of $\mathcal{S}$, where each record $v\in\mathcal{S}$ is sampled into $X$ independently with probability $\textbf{p}(v)$. The goal is to store $\mathcal{S}$ in a data structure to answer queries efficiently. If $\mathcal{S}$ fits in memory, the problem is interesting when $\mathcal{S}$ is dynamic. We develop a dynamic data structure with $\mathcal{O}(1+μ_{\mathcal{S}})$ expected \emph{query} time, $\mathcal{O}(n)$ space and $\mathcal{O}(1)$ amortized expected \emph{update}, \emph{insert} and \emph{delete} time, where $μ_{\mathcal{S}}=\sum_{v\in\mathcal{S}}\textbf{p}(v)$. The query time and space are optimal. If $\mathcal{S}$ does not fit in memory, the problem is difficult even if $\mathcal{S}$ is static. Under this scenario, we present an I/O-efficient algorithm that answers a \emph{query} in $\mathcal{O}\left((\log^*_B n)/B+(μ_\mathcal{S}/B)\log_{M/B} (n/B)\right)$ amortized expected I/Os using $\mathcal{O}(n/B)$ space, where $M$ is the memory size, $B$ is the block size and $\log^*_B n$ is the number of iterative $\log_2(.)$ operations we need to perform on $n$ before going below $B$. In addition, when each record is associated with a real-valued key, we extend the \emph{subset sampling} problem to the \emph{range subset sampling} problem, in which we require that the keys of the sampled records fall within a specified input range $[a,b]$. For this extension, we provide a solution under the dynamic setting, with $\mathcal{O}(\log n+μ_{\mathcal{S}\cap[a,b]})$ expected \emph{query} time, $\mathcal{O}(n)$ space and $\mathcal{O}(\log n)$ amortized expected \emph{update}, \emph{insert} and \emph{delete} time.

cs.DS↗

arXiv2022

A Practical Two-stage Ranking Framework for Cross-market Recommendation

Cross-market recommendation aims to recommend products to users in a resource-scarce target market by leveraging user behaviors from similar rich-resource markets, which is crucial for E-commerce companies but receives less research attention. In this paper, we present our detailed solution adopted in the cross-market recommendation contest, i.e., WSDM CUP 2022. To better utilize collaborative signals and similarities between target and source markets, we carefully consider multiple features as well as stacking learning models consisting of deep graph recommendation models (Graph Neural Network, DeepWalk, etc.) and traditional recommendation models (ItemCF, UserCF, Swing, etc.). Furthermore, We adopt tree-based ensembling methods, e.g., LightGBM, which show superior performance in prediction task to generate final results. We conduct comprehensive experiments on the XMRec dataset, verifying the effectiveness of our model. The proposed solution of our team WSDM_Coggle_ is selected as the second place submission.

cs.IR↗

arXiv2020

Joint learning of interpretation and distillation

The extra trust brought by the model interpretation has made it an indispensable part of machine learning systems. But to explain a distilled model's prediction, one may either work with the student model itself, or turn to its teacher model. This leads to a more fundamental question: if a distilled model should give a similar prediction for a similar reason as its teacher model on the same input? This question becomes even more crucial when the two models have dramatically different structure, taking GBDT2NN for example. This paper conducts an empirical study on the new approach to explaining each prediction of GBDT2NN, and how imitating the explanation can further improve the distillation process as an auxiliary learning task. Experiments on several benchmarks show that the proposed methods achieve better performance on both explanations and predictions.

cs.LG↗