# Towards Relaxed Multimodal Inputs for Gait-based Parkinson's Disease Assessment

arXiv: https://arxiv.org/abs/2510.15748 · HTML: https://mlsanity.com/paper/2510.15748/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 75 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Multi-Task Learning as a Bargaining Game](https://mlsanity.com/paper/2202.01017/) (2022)
- [Attentive Single-Tasking of Multiple Tasks](https://mlsanity.com/paper/1904.08918/) (2019)
- [Learning the Pareto Front with Hypernetworks](https://mlsanity.com/paper/2010.04104/) (2020)
- [Scalable Pareto Front Approximation for Deep Multi-Objective Learning](https://mlsanity.com/paper/2103.13392/) (2021)
- [Fair Resource Allocation in Multi-Task Learning](https://mlsanity.com/paper/2402.15638/) (2024)
- [FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space](https://mlsanity.com/paper/2310.20071/) (2023)
- [Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization](https://mlsanity.com/paper/2206.04496/) (2022)
- [Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models](https://mlsanity.com/paper/2210.09759/) (2022)
- [A Closer Look at Multimodal Representation Collapse](https://mlsanity.com/paper/2505.22483/) (2025)
- [Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling](https://mlsanity.com/paper/2312.01017/) (2023)
- [Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers](https://mlsanity.com/paper/2506.07986/) (2025)
- [Deep 1D-Convnet for accurate Parkinson disease detection and severity prediction from gait](https://mlsanity.com/paper/1910.11509/) (2019)
- [Multimodal feature fusion for CNN-based gait recognition: an empirical comparison](https://mlsanity.com/paper/1806.07753/) (2018)
- [Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences](https://mlsanity.com/paper/2407.08056/) (2024)
- [Using AI to Measure Parkinson's Disease Severity at Home](https://mlsanity.com/paper/2303.17573/) (2023)
- [Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion](https://mlsanity.com/paper/2406.09770/) (2024)
- [Efficient Pareto Manifold Learning with Low-Rank Structure](https://mlsanity.com/paper/2407.20734/) (2024)
- [Multimodal Gait Recognition for Neurodegenerative Diseases](https://mlsanity.com/paper/2101.02469/) (2021)
- [A Survey of Artificial Intelligence in Gait-Based Neurodegenerative Disease Diagnosis](https://mlsanity.com/paper/2405.13082/) (2024)

## Built on by (most cited first, 1 of 1)

- [MOSAIC: Modality-Specific Adaptation for Incremental Continual Learning in Parkinson's Disease Gait Assessment](https://mlsanity.com/paper/2606.13258/) (2026)

## Abstract (arXiv)

Parkinson's disease assessment has garnered growing interest in recent years, particularly with the advent of sensor data and machine learning techniques. Among these, multimodal approaches have demonstrated strong performance by effectively integrating complementary information from various data sources. However, two major limitations hinder their practical application: (1) the need to synchronize all modalities during training, and (2) the dependence on all modalities during inference. To address these issues, we propose the first Parkinson's assessment system that formulates multimodal learning as a multi-objective optimization (MOO) problem. This not only allows for more flexible modality requirements during both training and inference, but also handles modality collapse issue during multimodal information fusion. In addition, to mitigate the imbalance within individual modalities, we introduce a margin-based class rebalancing strategy to enhance category learning. We conduct extensive experiments on three public datasets under both synchronous and asynchronous settings. The results show that our framework-Towards Relaxed InPuts (TRIP)-achieves state-of-the-art performance, outperforming the best baselines by 16.48, 6.89, and 11.55 percentage points in the asynchronous setting, and by 4.86 and 2.30 percentage points in the synchronous setting, highlighting its effectiveness and adaptability.