Multimodal learning with graphs.

ABSTRACT: Artificial intelligence for graphs has achieved remarkable success in modeling complex systems, ranging from dynamic networks in biology to interacting particle systems in physics. However, the increasingly heterogeneous graph datasets call for multimodal methods that can combine different inductive biases-the set of assumptions that algorithms use to make predictions for inputs they have not encountered during training. Learning on multimodal datasets presents fundamental challenges because the inductive biases can vary by data modality and graphs might not be explicitly given in the input. To address these challenges, multimodal graph AI methods combine different modalities while leveraging cross-modal dependencies using graphs. Diverse datasets are combined using graphs and fed into sop

SUBMITTER: Ektefaie Y 

PROVIDER: S-EPMC10704992 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature