发表机构
Oakland University（奥克兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究通过受控的MV-GTA模型，在BBBP和BACE数据集上验证了显式标签和性质路由的有效性，发现联合模型在多任务nDCG上优于单独专家，但未支持自由形式路由等结论。
AI 中文摘要
图-文本检索通常将图及其描述映射到单个嵌入，即使查询仅涉及一个语义方面（如类别标签或分子性质）。多头可分离这些方面，但即使错误文本发送到对应查询头，查询头的改变也可能改变检索结果，这种行为体现的是架构信道化，而非必然的语义路由。本文研究可区分该差异的条件。本文的受控版本MV-GTA使用确定性、可验证的文本片段、独立的文本编码器、视图特定的图头，以及从外部标签或RDKit描述符推导的相关性。正确路由和逐样本打乱构成检索是否依赖内容的因果检验。在BBBP和BACE数据集上，与打乱训练相比，正确路由使标签和性质nDCG提升0.305至0.685；预期图头比最佳错误图头高0.303至0.453。拓扑在两个数据集间未一致专业化。在匹配的三种子比较中，一个联合模型的拓扑、标签、性质nDCG均值为0.720/1.000/0.877；三个单独训练的Single specialists为0.633/0.976/0.859。性质释义增强使未见过模板的nDCG比匹配暴露的标准对照分别提升0.140和0.147，但一致性和硬模板扩展在部分设置中会降低标准检索。因此，证据仅支持显式、外部基础的标签和性质路由及观察到的多接口整合，未确立自由形式路由、一致的三视图专业化、与专家的统计等价性或更优的下游预测。
英文摘要
Graph-text retrieval typically maps a graph and its description to a single embedding, even when a query concerns only one semantic aspect, such as a class label or molecular property. Multiple heads can separate these aspects, but a change in the query head may alter retrieval even when the wrong text is sent to that head. Such behavior demonstrates architectural channelization, not necessarily semantic routing. We examine the conditions under which this distinction can be resolved. Our controlled version of MV-GTA uses deterministic, verifiable text segments; isolated text encoders; view-specific graph heads; and relevance derived from external labels or RDKit descriptors. Correct routing and per-sample derangements form a causal test of whether retrieval depends on content. On BBBP and BACE, correct routing improves label and property nDCG by 0.305 to 0.685 over deranged training. The expected graph head exceeds the best wrong head by 0.303 to 0.453. Topology does not specialize consistently across the two datasets. In a matched three-seed comparison, one joint model obtains mean topology, label, and property nDCG of 0.720/1.000/0.877; three separately trained Single specialists obtain 0.633/0.976/0.859. Property paraphrase augmentation also improves unseen-template nDCG by 0.140 and 0.147 over a matched-exposure canonical control. Consistency and hard-template extensions, however, reduce canonical retrieval in some settings. The evidence is therefore limited to explicit, externally grounded label and property routing and observed multi-interface consolidation. It does not establish free-form routing, consistent three-view specialization, statistical equivalence to specialists, or superior downstream prediction.
