Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships

arXiv:2403.17173v1 Announce Type: new
Abstract: Modeling and visualizing relationships between tasks or datasets is an important step towards solving various meta-tasks such as dataset discovery, multi-tasking, and transfer learning. However, many relationships, such as containment and transferability, are naturally asymmetric and current approaches for representation and visualization (e.g., t-SNE do not readily support this. We propose Task2Box, an approach to represent tasks using box embeddings -- axis-aligned hyperrectangles in low dimensional spaces -- that can capture asymmetric relationships between them …

abstract arxiv box cs.cv current dataset datasets discovery embeddings however meta modeling relationships representation tasks transfer transfer learning type visualization