Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.09428 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910383848030208 |
|---|---|
| author | Zhi, Zhuo Liu, Ziquan Elbadawi, Moe Daneshmend, Adam Orlu, Mine Basit, Abdul Demosthenous, Andreas Rodrigues, Miguel |
| author_facet | Zhi, Zhuo Liu, Ziquan Elbadawi, Moe Daneshmend, Adam Orlu, Mine Basit, Abdul Demosthenous, Andreas Rodrigues, Miguel |
| contents | Multimodal machine learning with missing modalities is an increasingly relevant challenge arising in various applications such as healthcare. This paper extends the current research into missing modalities to the low-data regime, i.e., a downstream task has both missing modalities and limited sample size issues. This problem setting is particularly challenging and also practical as it is often expensive to get full-modality data and sufficient annotated training samples. We propose to use retrieval-augmented in-context learning to address these two crucial issues by unleashing the potential of a transformer's in-context learning ability. Diverging from existing methods, which primarily belong to the parametric paradigm and often require sufficient training samples, our work exploits the value of the available full-modality data, offering a novel perspective on resolving the challenge. The proposed data-dependent framework exhibits a higher degree of sample efficiency and is empirically demonstrated to enhance the classification model's performance on both full- and missing-modality data in the low-data regime across various multimodal learning tasks. When only 1% of the training data are available, our proposed method demonstrates an average improvement of 6.1% over a recent strong baseline across various datasets and missing states. Notably, our method also reduces the performance gap between full-modality and missing-modality data compared with the baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_09428 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity Zhi, Zhuo Liu, Ziquan Elbadawi, Moe Daneshmend, Adam Orlu, Mine Basit, Abdul Demosthenous, Andreas Rodrigues, Miguel Machine Learning Multimodal machine learning with missing modalities is an increasingly relevant challenge arising in various applications such as healthcare. This paper extends the current research into missing modalities to the low-data regime, i.e., a downstream task has both missing modalities and limited sample size issues. This problem setting is particularly challenging and also practical as it is often expensive to get full-modality data and sufficient annotated training samples. We propose to use retrieval-augmented in-context learning to address these two crucial issues by unleashing the potential of a transformer's in-context learning ability. Diverging from existing methods, which primarily belong to the parametric paradigm and often require sufficient training samples, our work exploits the value of the available full-modality data, offering a novel perspective on resolving the challenge. The proposed data-dependent framework exhibits a higher degree of sample efficiency and is empirically demonstrated to enhance the classification model's performance on both full- and missing-modality data in the low-data regime across various multimodal learning tasks. When only 1% of the training data are available, our proposed method demonstrates an average improvement of 6.1% over a recent strong baseline across various datasets and missing states. Notably, our method also reduces the performance gap between full-modality and missing-modality data compared with the baseline. |
| title | Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.09428 |