

























Abstract:Event-Based Models (EBMs) infer biomarker progression from cross-sectional data but typically only as ordinal sequences and rely on rigid model assumptions. We propose \textsc{Tempo}, a Transformer architecture that learns both ordinal and continuous event sequences through simulation-based supervised learning. \textsc{Tempo} uses two Transformer modules: one treats biomarkers as tokens to infer event sequencing; the other treats patients as tokens, representing each by their per-biomarker abnormality profile, to infer patients' disease stages. On synthetic benchmarks, \textsc{Tempo} reduces normalized Kendall's Tau distance by 52.89\% and staging MAE by 25.33\% compared to state-of-the-art SA-EBM, with larger reductions in high-dimensional settings (58.88\% and 61.10\%). Applied to ADNI, \textsc{Tempo} recovers a biologically plausible Alzheimer's progression: early medial temporal atrophy, followed by amyloid accumulation and cognitive decline, and late-stage tau pathology with terminal acceleration of global neurodegeneration -- broadly consistent with established disease models. \textsc{Tempo} also eliminates the need to derive custom inference algorithms and enables rapid empirical comparison of generative hypotheses.
| Comments: | 31 pages; Published at Conference on Health, Inference, and Learning (CHIL) 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.23368 [cs.LG] |
| (or arXiv:2604.23368v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.23368 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Proceedings of Machine Learning Research, 333, 2026 |
From: Hongtao Hao [view email]
[v1]
Sat, 25 Apr 2026 16:25:08 UTC (451 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。