Community Search in Time-dependent Road-social Attributed Networks

2025-05-18

AI Summary

Real-world community search often neglects the synergistic effects of keyword semantics, geographic proximity, and dynamic traffic-aware travel times, resulting in low semantic/spatial cohesion and poor adaptability to time-varying road networks; meanwhile, existing indexing schemes require full-graph traversal, leading to inefficiency. To address these issues, we propose a semantic–spatiotemporal-aware *k*-core community discovery model: (i) it jointly incorporates keyword semantic similarity (derived from large language model embeddings), geographic proximity, and time-dependent edge weights (modeling real-time traffic conditions); (ii) it introduces a local graph expansion algorithm that explores only the query node’s neighborhood, eliminating irrelevant traversals; and (iii) it refines *k*-core decomposition to simultaneously optimize structural cohesiveness, semantic consistency, and time-varying spatial connectivity. Extensive experiments demonstrate that our method significantly outperforms baseline approaches across all three dimensions—semantic relevance, spatial compactness, and temporal adaptability.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Distributed Search

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Community question answering

Abstract

Real-world networks often involve both keywords and locations, along with travel time variations between locations due to traffic conditions. However, most existing cohesive subgraph-based community search studies utilize a single attribute, either keywords or locations, to identify communities. They do not simultaneously consider both keywords and locations, which results in low semantic or spatial cohesiveness of the detected communities, and they fail to account for variations in travel time. Additionally, these studies traverse the entire network to build efficient indexes, but the detected community only involves nodes around the query node, leading to the traversal of nodes that are not relevant to the community. Therefore, we propose the problem of discovering semantic-spatial aware k-core, which refers to a k-core with high semantic and time-dependent spatial cohesiveness containing the query node. To address this problem, we propose an exact and a greedy algorithm, both of which gradually expand outward from the query node. They are local methods that only access the local part of the attributed network near the query node rather than the entire network. Moreover, we design a method to calculate the semantic similarity between two keywords using large language models. This method alleviates the disadvantages of keyword-matching methods used in existing community search studies, such as mismatches caused by differently expressed synonyms and the presence of irrelevant words. Experimental results show that the greedy algorithm outperforms baselines in terms of structural, semantic, and time-dependent spatial cohesiveness.

Problem

• Identify communities with high semantic and time-dependent spatial cohesiveness
• Overcome limitations of single-attribute community search methods
• Develop local algorithms avoiding full network traversal

Innovation

• Local expansion from query node for efficiency
• Semantic similarity via large language models
• Time-dependent spatial cohesiveness in k-core