Papers › Weight Averaging Improves Knowledge Distillation under Domain Shift

Weight Averaging Improves Knowledge Distillation under Domain Shift

20 Sep 2023arXiv:2309.11446archive 2025-07-28

Valeriy Berezovskiy, Nikita Morozov

Knowledge distillation (KD) is a powerful model compression technique broadly used in practical deep learning applications. It is focused on training a small student network to mimic a larger teacher network. While it is widely known that KD can offer an improvement to student generalization in i.i.d setting, its performance under domain shift, i.e. the performance of student networks on data from domains unseen during training, has received little attention in the literature. In this paper we make a step towards bridging the research fields of knowledge distillation and domain generalization. We show that weight averaging techniques proposed in domain generalization literature, such as SWAD and SMA, also improve the performance of knowledge distillation under domain shift. In addition, we propose a simplistic weight averaging strategy that does not require evaluation on validation data during training and show that it performs on par with SWAD and SMA when applied to KD. We name our final distillation approach Weight-Averaged Knowledge Distillation (WAKD).

PaperPDFCode

Code

vorobeevich/distillation-in-dg 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

Domain GeneralizationKnowledge Distillation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization Office-Home WAKD (DeiT-Ti) Average Accuracy 70.5 #31 of 45 Archive leaderboard report
Domain Generalization Office-Home WAKD (Resnet-18) Average Accuracy 66.7 #40 of 45 Archive leaderboard report
Domain Generalization PACS WAKD (DeiT-Ti) Average Accuracy 87.6 #36 of 133 Archive leaderboard report
Domain Generalization PACS WAKD (Resnet-18) Average Accuracy 86.6 #46 of 133 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

DeiTKnowledge DistillationStochastic Weight Averaging

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