arXiv：cs.LG· Yuanhao Zhuo, Zixi Qin, Ling Qin, Wanqing Li·· 2 小时前
BFHD：面向异构临床评估的双向特征协调分解
BFHD: Bidirectional Feature Harmonization Decomposition for Heterogeneous Clinical Assessments
AI 导读
研究者提出 BFHD（双向特征协调分解），将临床评估协调建模为测量级双向可恢复性问题，通过双向耦合翻译与特征级输出门控，在原始测量空间中显式分离可翻译与不可翻译成分。在合成数据和真实临床评估配对上的实验显示，BFHD 相比基线取得更广的可行协调覆盖和更好的子集稳定性。该论文为 IJCAI-ECAI 2026 收录论文的扩展版，共 17 页。
正文
Abstract:Clinical assessments are often collected using heterogeneous assessment systems across centers and time, leading to records that mix different but related sets of measurements. This motivates harmonization beyond total-score linking. We formulate clinical harmonization at the measurement level as a bidirectional recoverability problem: given paired observations from two assessment systems, the goal is to identify which measurements can be reliably translated in both directions within an application-defined tolerance, while separating non-translatable components. We propose Bidirectional Feature Harmonization Decomposition (BFHD), a feasibility-driven framework that enforces bidirectionally coupled translation and uses feature-wise output gating to produce an explicit decomposition in the original measurement space. Experiments on synthetic data and real clinical assessment pairs show that BFHD achieves broader feasible harmonization coverage and improved subset stability compared to baselines.
| Comments: | 17 pages, 2 figures, 9 tables. Extended version of the paper published in IJCAI-ECAI 2026, including additional supplementary material in the appendices |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.19352 [cs.LG] |
| (or arXiv:2610.19352v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19352 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-26), pp. 7046-7054, 2026 |
| Related DOI: | https://doi.org/10.24963/ijcai.2026/784
DOI(s) linking to related resources |
Submission history
From: Yuanhao Zhuo [view email]
[v1]
Wed, 14 Oct 2026 00:52:39 UTC (214 KB)
来源：arXiv：cs.LG · arxiv.org