Transfer Learning with Reconstruction Loss

arXiv:2404.00505v1 Announce Type: new
Abstract: In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective. However, in many scenarios, several distinct yet correlated objectives or tasks often need to be optimized on the same set of problem inputs. Instead of independently training a different neural network for each problem separately, it would be more efficient to exploit the correlations between these objectives and to train multiple neural network models with …

abstract applications arxiv cs.ai cs.lg cs.ni however inputs loss networks neural networks optimization set stat.ml tasks training transfer transfer learning type