{"ID":2848331,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.25091","arxiv_id":"2510.25091","title":"H3M-SSMoEs: Hypergraph-based Multimodal Learning with LLM Reasoning and Style-Structured Mixture of Experts","abstract":"Stock movement prediction remains fundamentally challenging due to complex temporal dependencies, heterogeneous modalities, and dynamically evolving inter-stock relationships. Existing approaches often fail to unify structural, semantic, and regime-adaptive modeling within a scalable framework. This work introduces H3M-SSMoEs, a novel Hypergraph-based MultiModal architecture with LLM reasoning and Style-Structured Mixture of Experts, integrating three key innovations: (1) a Multi-Context Multimodal Hypergraph that hierarchically captures fine-grained spatiotemporal dynamics via a Local Context Hypergraph (LCH) and persistent inter-stock dependencies through a Global Context Hypergraph (GCH), employing shared cross-modal hyperedges and Jensen-Shannon Divergence weighting mechanism for adaptive relational learning and cross-modal alignment; (2) a LLM-enhanced reasoning module, which leverages a frozen large language model with lightweight adapters to semantically fuse and align quantitative and textual modalities, enriching representations with domain-specific financial knowledge; and (3) a Style-Structured Mixture of Experts (SSMoEs) that combines shared market experts and industry-specialized experts, each parameterized by learnable style vectors enabling regime-aware specialization under sparse activation. Extensive experiments on three major stock markets demonstrate that H3M-SSMoEs surpasses state-of-the-art methods in both superior predictive accuracy and investment performance, while exhibiting effective risk control. Datasets, source code, and model weights are available at our GitHub repository: https://github.com/PeilinTime/H3M-SSMoEs.","short_abstract":"Stock movement prediction remains fundamentally challenging due to complex temporal dependencies, heterogeneous modalities, and dynamically evolving inter-stock relationships. Existing approaches often fail to unify structural, semantic, and regime-adaptive modeling within a scalable framework. This work introduces H3M...","url_abs":"https://arxiv.org/abs/2510.25091","url_pdf":"https://arxiv.org/pdf/2510.25091v1","authors":"[\"Peilin Tan\",\"Liang Xie\",\"Churan Zhi\",\"Dian Tu\",\"Chuanqi Shi\"]","published":"2025-10-29T01:54:52Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Mixture of Experts\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":607612,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2848331,"paper_url":"https://arxiv.org/abs/2510.25091","paper_title":"H3M-SSMoEs: Hypergraph-based Multimodal Learning with LLM Reasoning and Style-Structured Mixture of Experts","repo_url":"https://github.com/PeilinTime/H3M-SSMoEs","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}