Papers › Inter-choice dependent super-network weights

Inter-choice dependent super-network weights

23 Apr 2021arXiv:2104.11522archive 2025-07-28

Kevin Alexander Laube, Andreas Zell

The automatic design of architectures for neural networks, Neural Architecture Search, has gained a lot of attention over the recent years, as the thereby created networks repeatedly broke state-of-the-art results for several disciplines. The network search spaces are often finite and designed by hand, in a way that a fixed and small number of decisions constitute a specific architecture. Given these circumstances, inter-choice dependencies are likely to exist and affect the network search, but are unaccounted for in the popular one-shot methods. We extend the Single-Path One-Shot search-networks with additional weights that depend on combinations of choices and analyze their effect. Experiments in NAS-Bench 201 and SubImageNet based search spaces show an improved super-network performance in only-convolutions settings and that the overhead is nearly negligible for sequential network designs.

PaperPDFCode

Code

cogsys-tuebingen/uninas officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Neural Architecture Search

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections