Query cost estimation in graph databases via emphasizing query dependencies by using a neural reasoning network

Abstract

SummaryWith the increasing complexity of graph queries, query cost estimation has become a key challenge in graph databases. Accurate estimation results are critical for database administrators or database management systems to perform query processing or optimization tasks. An efficient and accurate estimation model can improve the estimation quality and make the produced results credible. Although learning‐based methods have been applied in query cost estimation, most of them are directed at relational queries and cannot be directly used for graph queries. Furthermore, most estimation approaches focus on the correlations between predicates or columns. The dependencies between query schema and query filter conditions and the correlation between query schema are ignored. In this study, we construct a novel deep learning model composed of reasoning and retrieval processes that can accurately capture the potential logical relationships in graph queries. This solves the above problems to some extent. In addition, we propose a query estimation framework that divides the estimation task into query workload generation, training data collection, feature extraction and encoding, and estimation model construction. The results of the experiment on real‐world datasets show that our estimation model can improve the estimation quality and outperforms other compared deep learning models in terms of estimation accuracy.

A Cardinality Estimator in Complex Database Systems Based on TreeLSTM

“…Equation ( 9) indicates that different types of sub-networks are selected according to the operator node. In Equation (10), C(k) represents the set of children of node k, and N(k) represents the number of children of node k. hroot is a vector representation of the root node. w t is the table name vector mentioned in Section 3.3.1.…”

“…With the development of machine learning techniques, researchers have also been using machine learning in recent years to address the problem of inaccurate cardinality estimation [6][7][8][9][10]. The multi-set convolutional neural network (MSCN) [7] is the current state-of-the-art method.…”

Convolutional Models with Multi-Feature Fusion for Effective Link Prediction in Knowledge Graph Embedding

“…The primary objective of link prediction is to infer new edges by leveraging the existing graph structure, entity attributes, or embeddings obtained with KGE methods. The importance of link prediction stems from its broad range of applications across various domains, such as social network analysis [4][5][6], recommender systems [7,8], bioinformatics [9], and knowledge base completion (KBC) [10,11]. By identifying missing or unknown links, link prediction enhances the quality and completeness of knowledge graphs, enabling more effective reasoning and decision making in various AI and NLP tasks [12][13][14][15].…”