Spectral Graph Filtering for Modality-Specific Representation Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908874537172992 |
|---|---|
| author | Yoffe, Shira Moscovich, Amit Jaffe, Ariel |
| author_facet | Yoffe, Shira Moscovich, Amit Jaffe, Ariel |
| contents | Multimodal datasets, where measurements are obtained from multiple sensors, have become central to many scientific domains. In unsupervised settings, most representation learning methods focus on identifying shared latent structures, such as clusters or continuous processes that appear across modalities. However, some aspects of the data may be observed only through a single modality. For example, in computational biology, certain cell-subtypes may appear in genetic profiles but not in epigenetic markers. In this paper, we present DELVE, a spectral method for extracting modality-specific (differential) latent variables. Our approach constructs a graph for each modality and leverages differences in their connectivity patterns to design a graph filter that attenuates shared signals while preserving modality-specific components. We provide an asymptotic convergence analysis for our method under a product manifold model. To evaluate the performance of our method, we test its ability to recover differential latent structures in several synthetic and real datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18741 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spectral Graph Filtering for Modality-Specific Representation Learning Yoffe, Shira Moscovich, Amit Jaffe, Ariel Methodology 62H25, 62R30 Multimodal datasets, where measurements are obtained from multiple sensors, have become central to many scientific domains. In unsupervised settings, most representation learning methods focus on identifying shared latent structures, such as clusters or continuous processes that appear across modalities. However, some aspects of the data may be observed only through a single modality. For example, in computational biology, certain cell-subtypes may appear in genetic profiles but not in epigenetic markers. In this paper, we present DELVE, a spectral method for extracting modality-specific (differential) latent variables. Our approach constructs a graph for each modality and leverages differences in their connectivity patterns to design a graph filter that attenuates shared signals while preserving modality-specific components. We provide an asymptotic convergence analysis for our method under a product manifold model. To evaluate the performance of our method, we test its ability to recover differential latent structures in several synthetic and real datasets. |
| title | Spectral Graph Filtering for Modality-Specific Representation Learning |
| topic | Methodology 62H25, 62R30 |
| url | https://arxiv.org/abs/2402.18741 |