FastER: Fast On-Demand Entity Resolution in Property Graphs

2025-04-02

AI Summary

Entity resolution (ER) on large-scale attributed graphs suffers from poor real-time performance and high computational overhead—especially in “on-demand ER,” where users require resolution only over local subgraphs. This paper proposes the first on-demand ER framework for attributed graphs. First, it introduces Graph Differential Dependencies (GDDs), a unified model jointly capturing structural and attribute semantics. Second, it constructs a blocking graph and incorporates Progressive Profile Scheduling (PPS) to enable streaming result delivery. Third, it integrates subgraph filtering, attributed graph embedding, and similarity-based pruning to achieve efficient pairwise matching. Evaluated on multiple benchmark datasets, the method reduces response latency by one to two orders of magnitude over state-of-the-art approaches, delivers the first result in milliseconds, and maintains high accuracy.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Search and Optimization: Distributed Search

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Entity resolution (ER) is the problem of identifying and linking database records that refer to the same real-world entity. Traditional ER methods use batch processing, which becomes impractical with growing data volumes due to high computational costs and lack of real-time capabilities. In many applications, users need to resolve entities for only a small portion of their data, making full data processing unnecessary -- a scenario known as"ER-on-demand". This paper proposes FastER, an efficient ER-on-demand framework for property graphs. Our approach uses graph differential dependencies (GDDs) as a knowledge encoding language to design effective filtering mechanisms that leverage both structural and attribute semantics of graphs. We construct a blocking graph from filtered subgraphs to reduce the number of candidate entity pairs requiring comparison. Additionally, FastER incorporates Progressive Profile Scheduling (PPS), allowing the system to incrementally produce results throughout the resolution process. Extensive evaluations on multiple benchmark datasets demonstrate that FastER significantly outperforms state-of-the-art ER methods in computational efficiency and real-time processing for on-demand tasks while ensuring reliability. We make FastER publicly available at: https://anonymous.4open.science/r/On_Demand_Entity_Resolution-9DFB

Problem

• Identifies and links database records referring to same entities
• Addresses inefficiency of batch processing in large datasets
• Enables real-time entity resolution for selective data portions

Innovation

• Uses graph differential dependencies for filtering
• Constructs blocking graph to reduce comparisons
• Incorporates Progressive Profile Scheduling