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.
Chengyang Luo, Zi-Xing Ding, Qing Liu et al.· Proceedings of the 32nd ACM...· 0 citations
Motivated by the observation that users in the real world often engage across multiple social networks simultaneously, we study the problem of influence maximization in multilayer social networks (Mlim), aiming to select a small set of nodes that maximizes the total influence spread across all layers. To this end, we introduce a hybrid propagation model that jointly captures layer-specific diffusion dynamics and probabilistic cross-layer propagation. Based on this model, we formally define the Mlim problem and establish its NP-hardness, monotonicity, and submodularity. To address the Mlim problem, we first propose a greedy baseline Mlim-Greedy, which achieves a (1-1/e) approximation. Since exact influence computation in Mlim-Greedy is #P-hard,we propose STARIM, a scalable algorithm with layer-weighted influence sampling that guarantees a (1 - 1/e - 𝔖) approximation. To further enhance efficiency, we design LGQIM, a two-stage framework where multilayer representation learning predicts influence spread from network structure, enabling deep reinforcement learning for adaptive seed selection. Extensive experiments on nine real-world datasets demonstrate that (1) STARIM is up to 2 orders of magnitude faster than the baselines while yielding 10%-30% improvement in influence spread, and (2) LGQIM further achieves an average 10× speedup over STARIM while maintaining comparable influence spread.
Xueqin Chang, Ruize Liu, Qing Liu et al.· Proceedings of the 32nd ACM...· 0 citations
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.
Chengyang Luo, Zi-Xing Ding, Qing Liu et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
