DISSECT: DISentangle SharablE ConTent for Multimodal Integration and Crosswise-mapping
Schau, G.; Burlingame, E. A.; Chang, Y. H.
Show abstract
Deep learning systems have emerged as powerful mechanisms for learning domain translation models. However, in many cases, complete information in one domain is assumed to be necessary for sufficient cross-domain prediction. In this work, we motivate a formal justification for domain-specific information separation in a simple linear case and illustrate that a self-supervised approach enables domain translation between data domains while filtering out domain-specific data features. We introduce a novel approach to identify domainspecific information from sets of unpaired measurements in complementary data domains by considering a deep learning cross-domain autoencoder architecture designed to learn shared latent representations of data while enabling domain translation. We introduce an orthogonal gate block designed to enforce orthogonality of input feature sets by explicitly removing non-sharable information specific to each domain and illustrate separability of domain-specific information on a toy dataset.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Deep learning models for COVID-19 chest x-ray classification: Preventing shortcut learning using feature disentanglement 93%
- Non-synaptic plasticity enables memory-dependent local learning 93%
- Towards explainable interaction prediction: Embedding biological hierarchies into hyperbolic interaction space 92%
Similar papers in this journal
- Single-Cell Multi-Modal GAN (scMMGAN) reveals spatial patterns in single-cell data from triple negative breast cancer 95%
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 94%
- Tokenized and Continuous Embedding Compressions of Protein Sequence and Structure 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.