Deep Regression Representation Learning with Topology

arXiv:2404.13904v1 Announce Type: new
Abstract: Most works studying representation learning focus only on classification and neglect regression. Yet, the learning objectives and therefore the representation topologies of the two tasks are fundamentally different: classification targets class separation, leading to disconnected representations, whereas regression requires ordinality with respect to the target, leading to continuous representations. We thus wonder how the effectiveness of a regression representation is influenced by its topology, with evaluation based on the Information Bottleneck (IB) principle.
The IB …

abstract arxiv class classification continuous cs.cv cs.lg focus regression representation representation learning studying targets tasks topology type