SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.07182 · NeurIPS · 2024

Revisiting Ensembling in One-Shot Federated Learning

Rachid Guerraoui, Nirupam Gupta, Rafael Pinot, Youssef Allouah, Anne-Marie Kermarrec, Rafael Pires, Rishi Sharma, Akash Dhasade

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 8 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
sacs-epfl/fens canonical 8 of 10
FunctionStatusWhere it lives
Meter Ran sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("5208240b1cd6c19b")
_evaluate Ran sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("93f4d96f2278b93b")
_one_hot Ran sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("d72787a1daa64a40")
_train_and_evaluate Ran sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("2ca89b3fc6a05a88")
comp_accuracy Ran sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("08b050ad57b64351")
evaluate_competencies_v2 Ran sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("05787e35341c7132")
get_num_classes Ran sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("2509af88160cc0c7")
get_prediction_using_competency Ran sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("8b6e33bdae2b5151")
_check_accuracy Not yet run sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("aafeb8a55133cbcc")
evaluate_all_aggregations Not yet run sacs-epfl/fens/aggregations.py
pointer only (licence: NONE) · get_code("6dea375bb6e99c59")

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 learning (FL) is an appealing approach to training machine learning models without sharing raw data. However, standard FL algorithms are iterative and thus induce a significant communication cost. One-shot federated learning (OFL) trades the iterative exchange of models between clients and the server with a single round of communication, thereby saving substantially on communication costs. Not surprisingly, OFL exhibits a performance gap in terms of accuracy with respect to FL, especially under high data heterogeneity. We introduce FENS, a novel federated ensembling scheme that approaches the accuracy of FL with the communication efficiency of OFL. Learning in FENS proceeds in two phases: first, clients train models locally and send them to the server, similar to OFL; second, clients collaboratively train a lightweight prediction aggregator model using FL. We showcase the effectiveness of FENS through exhaustive experiments spanning several datasets and heterogeneity levels. In the particular case of heterogeneously distributed CIFAR-10 dataset, FENS achieves up to a 26.9% higher accuracy over state-of-the-art (SOTA) OFL, being only 3.1% lower than FL. At the same time, FENS incurs at most 4.3× more communication than OFL, whereas FL is at least 10.9× more communication-intensive than FENS.

For agents

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

get_harvested_code_for_paper("2411.07182")
get_code_for_paper("2411.07182")
have("2411.07182")

Connect an agent — have() is free.