Papers › Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search

Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search

27 Nov 2019ECCV 2020 8arXiv:1911.12126archive 2025-07-28

Xiangxiang Chu, Tianbao Zhou, Bo Zhang, Jixiang Li

Differentiable Architecture Search (DARTS) is now a widely disseminated weight-sharing neural architecture search method. However, it suffers from well-known performance collapse due to an inevitable aggregation of skip connections. In this paper, we first disclose that its root cause lies in an unfair advantage in exclusive competition. Through experiments, we show that if either of two conditions is broken, the collapse disappears. Thereby, we present a novel approach called Fair DARTS where the exclusive competition is relaxed to be collaborative. Specifically, we let each operation's architectural weight be independent of others. Yet there is still an important issue of discretization discrepancy. We then propose a zero-one loss to push architectural weights towards zero or one, which approximates an expected multi-hot solution. Our experiments are performed on two mainstream search spaces, and we derive new state-of-the-art results on CIFAR-10 and ImageNet. Our code is available on https://github.com/xiaomi-automl/fairdarts .

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xiaomi-automl/fairdarts officialmentioned in papermentioned on GitHubpytorch 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

AutoMLNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search CIFAR-10 FairDARTS-a FLOPS 746M #24 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 FairDARTS-a Parameters 2.8M #24 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 FairDARTS-a Search Time (GPU days) 0.25 #24 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 FairDARTS-a Top-1 Error Rate 2.54% #24 of 41 Archive leaderboard report
Neural Architecture Search ImageNet FairDARTS-C MACs 386M #71 of 135 Archive leaderboard report
Neural Architecture Search ImageNet FairDARTS-C Top-1 Error Rate 22.8 #71 of 135 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

DARTSLSTMSigmoid ActivationSoftmaxTanh Activation

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