DS-Span: Single-Phase Discriminative Subgraph Mining for Efficient Graph Embeddings

2025-11-21

AI Summary

Existing discriminative subgraph mining methods suffer from multi-stage redundancy, high computational overhead, and weak coupling between subgraph structure and discriminative power. This paper proposes a single-stage end-to-end framework that jointly performs pattern growth, dynamic pruning, and supervised scoring, directly learning compact graph embeddings that encode both topological and semantic information. We innovatively introduce a coverage-constrained eligibility mechanism and an information-gain-guided selection strategy to adaptively restrict the search space and enhance class separability. By employing a single-pass search and supervision-driven scoring, our method significantly improves subgraph discriminability, compactness, and interpretability. Extensive experiments on multiple benchmark datasets demonstrate that our approach achieves comparable or superior classification accuracy while drastically reducing runtime—validating its efficiency and practicality.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in 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: Robustness and generalizability of Web mining methods

Abstract

Graph representation learning seeks to transform complex, high-dimensional graph structures into compact vector spaces that preserve both topology and semantics. Among the various strategies, subgraph-based methods provide an interpretable bridge between symbolic pattern discovery and continuous embedding learning. Yet, existing frequent or discriminative subgraph mining approaches often suffer from redundant multi-phase pipelines, high computational cost, and weak coupling between mined structures and their discriminative relevance. We propose DS-Span, a single-phase discriminative subgraph mining framework that unifies pattern growth, pruning, and supervision-driven scoring within one traversal of the search space. DS-Span introduces a coverage-capped eligibility mechanism that dynamically limits exploration once a graph is sufficiently represented, and an information-gain-guided selection that promotes subgraphs with strong class-separating ability while minimizing redundancy. The resulting subgraph set serves as an efficient, interpretable basis for downstream graph embedding and classification. Extensive experiments across benchmarks demonstrate that DS-Span generates more compact and discriminative subgraph features than prior multi-stage methods, achieving higher or comparable accuracy with significantly reduced runtime. These results highlight the potential of unified, single-phase discriminative mining as a foundation for scalable and interpretable graph representation learning.

Problem

• Reduces computational cost in discriminative subgraph mining
• Unifies pattern growth and supervision in single-phase framework
• Enhances interpretability and efficiency of graph embeddings

Innovation

• Single-phase discriminative subgraph mining framework
• Coverage-capped eligibility mechanism for exploration
• Information-gain-guided selection for class separation