更多视角，更强信号：面向多模态实体表示学习的多视角增强与渐进融合

中文摘要 AI 辅助

学习有效的多模态实体表示是多模态知识图谱补全（MMKGC）等推理任务的基础。然而，现有方法常面临模态内语义过平滑、跨模态噪声过滤无效的问题，尤其在数据稀疏或语义模糊的条件下更为突出。为克服这些局限，本文提出PrismF——一种将多视角增强与渐进融合相结合的统一框架，用于从多样输入中提取更强信号。PrismF通过多视角机制增强细粒度模态内语义，该机制将每个模态分解为互补视角，并通过解耦损失约束这些视角以降低表示崩溃风险。此外，它通过渐进融合策略改进跨模态集成，该策略动态校准模态间交互，使模型能够突出有用信号，同时抑制噪声或不可靠信号。在三个公共基准上的大量实验表明，PrismF实现了最强的整体性能，包括在KVC16K上的MRR相对提升4.04%、Hits@1相对提升11.17%。我们的代码可在此https URL获取。

英文摘要

Learning effective multimodal entity representations is fundamental for reasoning tasks such as multimodal knowledge graph completion (MMKGC). However, existing methods often suffer from semantic over-smoothing within modalities and ineffective noise filtration across modalities, particularly under sparse or ambiguous conditions. To overcome these limitations, we propose PrismF, a unified framework that synergizes multi-perspective enhancement with progressive fusion to extract stronger signals from diverse inputs. PrismF enhances fine-grained intra-modal semantics through a multi-perspective mechanism that decomposes each modality into complementary views and constrains them with a decoupling loss to reduce representation collapse. Furthermore, it improves cross-modal integration through a progressive fusion strategy that dynamically calibrates inter-modal interactions, enabling the model to emphasize informative signals while suppressing noisy or unreliable ones. Extensive experiments on three public benchmarks show that PrismF achieves the strongest overall performance, including relative improvements of 4.04% in MRR and 11.17% in Hits@1 on KVC16K. Our code can be found at https://github.com/HubuKG/PrismF.

发表机构

• School of Computer Science, Hubei University（湖北大学计算机学院）
• School of Cyber Science and Technology, Hubei University（湖北大学网络空间安全学院）
• Institute of Vocational Education, Guangdong Industry Polytechnic University（广东轻工职业技术学院职业教育学院）
• School of Computer Science, Hubei Key Laboratory of Big Data Intelligent Analysis and Application, Hubei University（湖北大学计算机学院、湖北省大数据智能分析与应用重点实验室）

机构由 AI 辅助整理，请以论文原文为准。