发表机构
Beijing Institute of Technology; Sun Yat-sen University; Shandong University（北京理工大学; 中山大学; 山东大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出MAG-SCOUT框架，在构建图前评估其预期效用，决定是否图化多模态数据，实验节省33.1%图工作并保留96.7%正增益。
AI 中文摘要
多模态图学习近来已成为一种有效的范式，用于将实体间关系纳入多模态表示中。现有研究在如何构建和优化图方面取得了实质性进展，但很少考虑一个更基本的问题：对于给定的数据集和任务，是否应该引入额外的关系结构。通过在多种数据集、任务和图构建器上的实证研究，我们发现图化并非始终有益：引入关系结构在某些情况下可以带来显著改进，而在其他情况下则只能提供有限甚至负面的收益。这一观察促使我们提出一个新视角：图构建应被视为基于其预期效用的选择性决策，而非默认的预处理步骤。为解决此问题，我们提出MAG-SCOUT，一种构建前图评估框架，在生成完整拓扑之前估计引入图结构是否有益。MAG-SCOUT收集有限的关系证据，分析其潜在的任务特定贡献，并估计图化的预期效用以及构建成本，以做出构建或跳过决策。在六个多模态数据集、三个下游任务和多种图构建器上的大量实验表明，MAG-SCOUT能有效识别何时应引入图结构，在预注册下限下节省33.1%的任务宏图工作，同时保留96.7%的保留正增益质量。
英文摘要
Multimodal graph learning has recently emerged as an effective paradigm for in corporating inter-entity relationships into multimodal representations. Existing studies have made substantial progress on how to construct and optimize graphs, but rarely consider a more fundamental question: whether additional relational structures should be introduced for a given dataset and task. Through empirical studies across diverse datasets, tasks, and graph constructors, we reveal that graphification is not consistently beneficial: introducing relational structures can provide substantial improvements in some cases, while offering limited or even negative gains. This observation motivates a new perspective that graph construction should be treated as a selective decision based on its expected utility rather than a default preprocessing step. To address this issue, we propose MAG-SCOUT, a pre-construction graph assessment framework that estimates whether introducing graph structures is beneficial before generating the complete topology. MAG-SCOUT collects limited relational evidence, analyzes its potential taskspecific contribution, and estimates the expected utility of graphification together with construction cost to make a build-or-skip decision. Extensive experiments across six multimodal datasets, three downstream tasks, and diverse graph constructors demonstrate that MAG-SCOUT effectively identifies when graph structures should be introduced, saving 33.1% of task-macro graph work while retaining 96.7% of held-out positive-gain mass under the pre-registered floor.
