ECHO: Adaptive Community Search over Multimodal Graphs
TL;DR
An adaptive community search framework ECHO is proposed, which consistently outperforms state-of-the-art methods in terms of community quality while achieving superior search efficiency.
Abstract
In this paper, for the first time, we study the community search problem over multimodal graphs. This task aims to identify a query vertex-containing subgraph that is both structurally cohesive and semantically coherent with multimodal query inputs (e.g., text and images). Existing community search methods fail to capture fine-grained multimodal semantics and do not support effective multimodal fusion. To address these limitations, we propose an adaptive community search framework ECHO, which includes two key components. (i) A Fine-grained Modality Extractor decomposes multimodal content into structured local semantic units to preserve details often lost in coarse representations, operating in an encoder-agnostic manner. (ii) A Dual-Track Mixture of Experts network decouples semantic and structural modeling into parallel tracks, utilizing a hierarchical MoE architecture for adaptive, query-aware feature fusion. Extensive experiments on real-world multimodal graphs demonstrate that ECHO consistently outperforms state-of-the-art methods in terms of community quality while achieving superior search efficiency.