SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.06349 · ICML · 2025

Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead

Si-Hyeon Lee, Won-Jun Jang, Hyeon-Seo Park

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 22 functions out of this paper's own repositories and ran 16 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
autonomousvision/stylegan-xl canonical 14 of 20
kuangliu/pytorch-cifar canonical 2 of 2
FunctionStatusWhere it lives
parse_tuple Ran autonomousvision/stylegan-xl/dataset_tool.py
code served (permissive licence) · get_code("9cd07419f7c926f8")
NormLayer Ran autonomousvision/stylegan-xl/pg_modules/blocks.py
code served (permissive licence) · get_code("ef1e7dffb5d433d4")
UpBlockBig Ran autonomousvision/stylegan-xl/pg_modules/blocks.py
code served (permissive licence) · get_code("f87cd99314206f72")
UpBlockSmall Ran autonomousvision/stylegan-xl/pg_modules/blocks.py
code served (permissive licence) · get_code("0186912dcb8b92b9")
drop_connect Ran kuangliu/pytorch-cifar/models/efficientnet.py
code served (permissive licence) · get_code("4304a326c593f8db")
file_ext Ran autonomousvision/stylegan-xl/dataset_tool.py
code served (permissive licence) · get_code("a2b45afa097b55b6")
forward_flex Ran autonomousvision/stylegan-xl/feature_networks/vit.py
code served (permissive licence) · get_code("562cccfa5027f008")
get_activation Ran autonomousvision/stylegan-xl/feature_networks/vit.py
code served (permissive licence) · get_code("1c094193a4506a40")
layout_grid Ran autonomousvision/stylegan-xl/gen_video.py
code served (permissive licence) · get_code("456c172851946697")
make_transform Ran autonomousvision/stylegan-xl/gen_images.py
code served (permissive licence) · get_code("f47dff4b7b27bba7")
maybe_min Ran autonomousvision/stylegan-xl/dataset_tool.py
code served (permissive licence) · get_code("dd1dc700e87f36cc")
parse_comma_separated_list Ran autonomousvision/stylegan-xl/calc_metrics.py
code served (permissive licence) · get_code("d01b68a634f71551")
parse_range Ran autonomousvision/stylegan-xl/gen_images.py
code served (permissive licence) · get_code("236de8614a178382")
parse_range Ran autonomousvision/stylegan-xl/gen_video.py
code served (permissive licence) · get_code("025e4c7cda618f25")
parse_vec2 Ran autonomousvision/stylegan-xl/gen_images.py
code served (permissive licence) · get_code("180016b9227381b1")
swish Ran kuangliu/pytorch-cifar/models/efficientnet.py
code served (permissive licence) · get_code("8737c82de631cffc")
ask_yes_no Not yet run autonomousvision/stylegan-xl/dnnlib/util.py
code served (permissive licence) · get_code("9d31d2c4cd16bb2d")
compute_is Not yet run autonomousvision/stylegan-xl/metrics/inception_score.py
code served (permissive licence) · get_code("fc49fa553c005268")
format_time Not yet run autonomousvision/stylegan-xl/dnnlib/util.py
code served (permissive licence) · get_code("053fc534bc6bb989")
format_time_brief Not yet run autonomousvision/stylegan-xl/dnnlib/util.py
code served (permissive licence) · get_code("77f4aa0649e7f404")
forward_vit Not yet run autonomousvision/stylegan-xl/feature_networks/vit.py
code served (permissive licence) · get_code("4c52162336ee4320")
parse_tuple Not yet run autonomousvision/stylegan-xl/gen_video.py
code served (permissive licence) · get_code("6a0f2095bdd516ab")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Federated ensemble distillation addresses client heterogeneity by generating pseudo-labels for an unlabeled server dataset based on client predictions and training the server model using the pseudo-labeled dataset. The unlabeled server dataset can either be pre-existing or generated through a data-free approach. The effectiveness of this approach critically depends on the method of assigning weights to client predictions when creating pseudo-labels, especially in highly heterogeneous settings. Inspired by theoretical results from GANs, we propose a provably near-optimal weighting method that leverages client discriminators trained with a server-distributed generator and local datasets. Our experiments on various image classification tasks demonstrate that the proposed method significantly outperforms baselines. Furthermore, we show that the additional communication cost, client-side privacy leakage, and client-side computational overhead introduced by our method are negligible, both in scenarios with and without a pre-existing server dataset.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.06349")
get_code_for_paper("2502.06349")
have("2502.06349")

Connect an agent — have() is free.