Crane: An Accurate and Scalable Neural Sketch for Graph Stream Summarization

2026-02-16

AI Summary

This work addresses the challenge of biased frequency estimation in memory-constrained graph streaming scenarios, where high-frequency items often obscure low-frequency ones. To mitigate this interference, the authors propose a hierarchical neural sketch architecture featuring an innovative layer-wise carry mechanism that progressively elevates high-frequency items across layers, thereby reducing intra-layer contention. The design is further enhanced with an adaptive memory expansion strategy that dynamically allocates resources according to the scale and dynamics of incoming graph streams. This approach effectively disentangles high- and low-frequency components, significantly improving both estimation accuracy and scalability. Experimental evaluations across diverse graph stream datasets—ranging from 20K to 60M edges—demonstrate that the proposed method reduces estimation error by nearly an order of magnitude compared to state-of-the-art alternatives.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Data Stream Mining
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic 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
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Graph streams are rapidly evolving sequences of edges that convey continuously changing relationships among entities, playing a crucial role in domains such as networking, finance, and cybersecurity. Their massive scale and high dynamism make obtaining accurate statistics challenging with limited memory constraints. Traditional methods summarize graph streams through hand-crafted sketches, while recent studies have begun to replace these sketches with neural counterparts to improve adaptability and accuracy. However, this shift faces a major challenge: under limited memory, dominant frequent items tend to overshadow rare ones, hindering the neural network's ability to recover accurate statistics. To address this, we propose Crane, a hierarchical neural sketch architecture for graph stream summarization. Crane uses a hierarchical carry mechanism that automatically elevates frequent items to higher memory layers, reducing interference between frequent and infrequent items within the same layer. To better accommodate real-world deployment, Crane further adopts an adaptive memory expansion strategy that dynamically adds new layers once the occupancy of the top layer exceeds a threshold, enabling scalability across diverse data magnitudes. Extensive experiments on various datasets ranging from 20K to 60M edges demonstrate that Crane reduces estimation error by roughly 10x compared to state-of-the-art methods.

Problem

• graph stream summarization
• neural sketch
• memory-constrained statistics
• frequent and rare items
• scalability

Innovation

• neural sketch
• graph stream summarization
• hierarchical carry mechanism
• adaptive memory expansion
• frequency estimation