MedFuse: Multiplicative Embedding Fusion For Irregular Clinical Time Series
Yi-Hsien Hsieh, Ta-Jung Chien, Chun-Kai Huang, Shao-Hua Sun, and Che Lin
TL;DR
MedFuse introduces a multiplicative embedding fusion method for irregular clinical time series, improving predictive performance and representation expressiveness over existing additive approaches in electronic health record data.
Contribution
The paper presents MuFuse, a novel multiplicative fusion module that captures higher-order feature interactions, enhancing modeling of irregular clinical time series.
Findings
Outperforms state-of-the-art baselines on real-world datasets
Enhances model expressiveness and feature interaction modeling
Supports effective cross-dataset pretraining
Abstract
Clinical time series derived from electronic health records (EHRs) are inherently irregular, with asynchronous sampling, missing values, and heterogeneous feature dynamics. While numerical laboratory measurements are highly informative, existing embedding strategies usually combine feature identity and value embeddings through additive operations, which constrains their ability to capture value-dependent feature interactions. We propose MedFuse, a framework for irregular clinical time series centered on the MuFuse (Multiplicative Embedding Fusion) module. MuFuse fuses value and feature embeddings through multiplicative modulation, preserving feature-specific information while modeling higher-order dependencies across features. Experiments on three real-world datasets covering both intensive and chronic care show that MedFuse consistently outperforms state-of-the-art baselines on key…
Peer Reviews
Decision·ICLR 2026 Conference Withdrawn Submission
- The motivation is clear. - The problem is interesting. - The paper is easy to read and understand.
- Insufficient experiments. - Novelty is limited. It is a technique that disentangles numerical values into two parts. But this has been done by others like FT-Transformer and TabTransformer-like series models.
The main contribution of fusion methods for irregular EHR data is an interesting and underexplored area. The paper generalizes the SUMMIT model, and the derivation is sound. The formulation and mathematical notation are generally clear presented. The overall paper is easy to read. The experiments are not just on ICU mortality prediction datasets, but also carcinoma, suggesting some generalizability. If the claims hold, the approach proposed in the paper can influence how numerical values are emb
The paper heavily relies on the claim that multiplicative fusion enables "richer feature-value interactions" and "nonlinear modulation," but provides limited evidence about its benefit for clinical data. The justification for multiplicative gating is also hand-wavy, and relevant only at the last layer. Since we have a transformer architecture with multiple layers, there is no reason to see why the relevant interaction cannot be learned under additive terms. Furthermore, there are multiple pape
1. The studie problem is interesting and important. Especially irregular time series analysis is a pretty challenging domain for clinical data analysis. 2. The proposed approach achieve good results on 3 different tasks.
1. The paper’s contribution appears incremental. Representing each feature at each timestamp as an embedding follows prior work in SUMMIT [1], as the authors acknowledge. The main novelty is the multiplicative fusion of the feature identifier and the value embedding. As presented, this reads more as a heuristic than a method: the paper does not explain why multiplication is preferable to alternatives such as addition, concatenation, gating, attention, or bilinear pooling. 2. Empirically, the ga
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning in Healthcare · Time Series Analysis and Forecasting · Electronic Health Records Systems