Lyapunov-Stable Adaptive Control for Multimodal Concept Drift
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912656783310848 |
|---|---|
| author | Pan, Tianyu Bell Zhu, Mengdi Cole, Alexa Jordyn Wilson, Ronald Woodard, Damon L. |
| author_facet | Pan, Tianyu Bell Zhu, Mengdi Cole, Alexa Jordyn Wilson, Ronald Woodard, Damon L. |
| contents | Multimodal learning systems often struggle in non-stationary environments due to concept drift, where changing data distributions can degrade performance. Modality-specific drifts and the lack of mechanisms for continuous, stable adaptation compound this challenge. This paper introduces LS-OGD, a novel adaptive control framework for robust multimodal learning in the presence of concept drift. LS-OGD uses an online controller that dynamically adjusts the model's learning rate and the fusion weights between different data modalities in response to detected drift and evolving prediction errors. We prove that under bounded drift conditions, the LS-OGD system's prediction error is uniformly ultimately bounded and converges to zero if the drift ceases. Additionally, we demonstrate that the adaptive fusion strategy effectively isolates and mitigates the impact of severe modality-specific drift, thereby ensuring system resilience and fault tolerance. These theoretical guarantees establish a principled foundation for developing reliable and continuously adapting multimodal learning systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15944 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lyapunov-Stable Adaptive Control for Multimodal Concept Drift Pan, Tianyu Bell Zhu, Mengdi Cole, Alexa Jordyn Wilson, Ronald Woodard, Damon L. Machine Learning Artificial Intelligence Multimodal learning systems often struggle in non-stationary environments due to concept drift, where changing data distributions can degrade performance. Modality-specific drifts and the lack of mechanisms for continuous, stable adaptation compound this challenge. This paper introduces LS-OGD, a novel adaptive control framework for robust multimodal learning in the presence of concept drift. LS-OGD uses an online controller that dynamically adjusts the model's learning rate and the fusion weights between different data modalities in response to detected drift and evolving prediction errors. We prove that under bounded drift conditions, the LS-OGD system's prediction error is uniformly ultimately bounded and converges to zero if the drift ceases. Additionally, we demonstrate that the adaptive fusion strategy effectively isolates and mitigates the impact of severe modality-specific drift, thereby ensuring system resilience and fault tolerance. These theoretical guarantees establish a principled foundation for developing reliable and continuously adapting multimodal learning systems. |
| title | Lyapunov-Stable Adaptive Control for Multimodal Concept Drift |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.15944 |