基于监督嵌入的症状网络可扩展部分信息分解
Scalable partial information decomposition for symptom networks via supervised embeddings
- University of Amsterdam（阿姆斯特丹大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出ePID，通过监督嵌入压缩症状网络实现可扩展部分信息分解，在PHQ-9和IRI数据上揭示冗余与协同贡献的差异，为症状网络分析提供新工具。
AI中文摘要：
心理健康症状之间的成对关系通常被概括为标量边权重，这无法表达两个症状是否携带关于第三个症状的重叠信息，或仅在组合中出现的信息。部分信息分解（PID）解决了这一缺口，但在超过少数几个源时计算上难以处理。我们引入了基于嵌入的PID（ePID），这是一种可扩展的流程，将所有非焦点症状压缩为低基数离散嵌入，并计算可处理的双源PID，为每个有序源-目标对生成源独有、余项独有、冗余和协同分量。我们在校准至PHQ-9的合成贝叶斯网络上以及跨五种PID度量的83个真实世界数据集上，对13种候选嵌入进行了基准测试。一种监督的凝聚条件信息瓶颈（ACIB）嵌入在13种测试嵌入中最准确地恢复了参考分解，并且在所有PID度量下，一旦压缩四个或更多症状，就产生非负原子（协同恢复r = 0.92）。随后，两种工具出现了显著分歧。在PHQ-9网络（UK Biobank，N = 154,291；新乡学生样本，N = 24,292）中，周围症状上下文通过冗余和余项独有通道承载了大部分成对依赖性；协同贡献了6%至9%，且两个队列中没有任何有向边是协同主导的。在28项人际反应指数中，45%的源对是协同主导的。相同的流程，在无参数更改的情况下应用，因此对两种工具返回了相反的特征，每种都与该工具的构建方式一致。通过分离重叠信息与交互依赖信息，ePID为标准症状网络方法提供了一种可扩展、模型无关的补充，以区分对观察到的相关性的冗余和协同贡献。
英文摘要：
Pairwise relationships among mental-health symptoms are routinely summarised asscalar edge weights, which cannot express whether two symptoms carry overlapping information about a third or information that appears only in combination. Partial information decomposition (PID) addresses this gap but is computationally intractable beyond a few sources. We introduce embedding-based PID (ePID), a scalable pipeline that compresses all nonfocal symptoms into a low-cardinality discrete embedding and computes a tractable two-source PID, yielding source-unique, remainder-unique, redundant, and synergistic components for each ordered source-target pair. We benchmarked 13 candidate embeddings on synthetic Bayesian networks calibrated to PHQ-9 and on 83 real-world datasets across five PID measures. A supervised Agglomerative Conditional Information Bottleneck (ACIB) embedding recovered the reference decomposition most accurately of the 13 embeddings tested, and did so for every PID measure yielding non-negative atoms once four or more symptoms were compressed (synergy recovery r = 0.92). The two instruments then diverged sharply. In PHQ-9 networks (UK Biobank,N = 154,291; Xinxiang student sample, N = 24,292) the surrounding symptom context carried most pairwise dependence through redundant and remainder-unique channels; synergy contributed 6 to 9%, and no directed edge was synergy-dominated in either cohort. In the 28-item Interpersonal Reactivity Index, 45% of source pairs were. The identical pipeline, applied without parameter changes, therefore returned opposite profiles for the two instruments, each consistent with how that instrument was constructed. By separating overlapping from interaction-dependent information, ePID provides a scalable, model-agnostic complement to standard symptom-network methodology to distinguish redundant and synergistic contributions to observed correlations.
