Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 3458-3469· 0 citations· 29 references
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.
Recent studies in multimodal recommendation, which leverage diverse modal information to address data sparsity and enhance recommendation accuracy, have garnered significant interest. Two critical processes in this domain are modality fusion and representation learning. In representation learning, existing studies ofte...
Jin-Feng Xu, Zhe-Yu Chen, Wei Wang et al.· ACM Transactions on Recommen...· 0 citations
To address the challenges of evidence chain breakage of vectors, collaborative constraint between image and structured fields is challenging, and the credibility of the generated results is insufficient with multimodal data, this paper proposes a GraphRAG semantic retrieval model for multimodal data. In order to realiz...
Chun-Jing Liao, Pei-Shan Ye, An-Ni Huang et al.· Discover Artificial Intellig...· 0 citations
DeepIDDFS is introduced, a scalable node embedding designed for ER in large and dynamic graphs that employs an iterative deepening depth-first search (IDDFS), integrates BERT-based semantic embeddings to handle noisy and inconsistent attributes, and incorporates a time-aware aggregation mechanism that emphasizes recent...
Nour Mekki, Djamel Berrabah, Abdelhamid Malki· Knowledge and Information Sy...· 1 citation
Traditional search engines struggle to synthesize fragmented information for complex queries, while generative AI search engines face challenges in relevance, comprehensiveness, and presentation. To address these limitations, we introduce Xinyu AI Search, a novel system that incorporates a query-decomposition graph to...
Bo Tang, Junyi Zhu, Ang Li et al.· Proceedings of the 32nd ACM...· 0 citations
Multimodal graph learning has become an important direction for modeling graph-structured data with heterogeneous node content, such as text and images. However, existing methods often rely on globally shared or weakly adaptive fusion strategies, which makes it difficult to model node-wise differences in modality usefu...
Shaohua Dong, Jia-Chun Chen, Wen-Jie Feng et al.· Fall Joint Computer Conferen...· 0 citations
ReCoG (Reciprocal Co-Evolution for Multimodal Graph Learning) is proposed, a new learning paradigm that tightly couples graph structure learning and multimodal representation learning through end-to-end reciprocal interaction and yields greater expressiveness than decoupled or two-stage formulations.
Rui Xue, Tianfu Wu· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
