Rethinking Neural Operations for Diverse Tasks

Author name not available (Why is that?)

Publication date: 29 March 2021

Abstract: An important goal of AutoML is to automate-away the design of neural networks on new tasks in under-explored domains. Motivated by this goal, we study the problem of enabling users to discover the right neural operations given data from their specific domain. We introduce a search space of operations called XD-Operations that mimic the inductive bias of standard multi-channel convolutions while being much more expressive: we prove that it includes many named operations across multiple application areas. Starting with any standard backbone such as ResNet, we show how to transform it into a search space over XD-operations and how to traverse the space using a simple weight-sharing scheme. On a diverse set of tasks -- solving PDEs, distance prediction for protein folding, and music modeling -- our approach consistently yields models with lower error than baseline networks and often even lower error than expert-designed domain-specific approaches.

Has companion code repository: https://github.com/nick11roberts/XD

This page was built for publication: Rethinking Neural Operations for Diverse Tasks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6364050)