FedSA (Parameter-efficient fine-tuning (LoRA family)): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 3 beat it on benchmarks — #63 of 1113 most-superseded. Sub-problem: cluster led by FFA-LoRA. Newer alternatives in the same sub-problem include Shift-Dependent Asymmetry, GLoRA, HiLoRA, FedRot-LoRA, ADF-LoRA.

Parameter-efficient fine-tuning (LoRA family)

FedSA

Superseded baseline#63 of 1,113 most-superseded

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 3 beat it on benchmarks

Beaten on benchmarks

Head-to-head results where a newer method reports beating FedSA. Values are copied from the source paper's tables — verify against the cited paper.

FedALT beats FedSA
67.55 vs 63.47
Average · [LLaMA2-7B]
FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRA
FedOPAL-R beats FedSA
0.870 vs 0.844
Balanced client test accuracy · [Camelyon17-WILDS task]
Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare
Shift-Dependent Asymmetry beats FedSA
84.52 vs 83.04
Avg · [Fundus photography images, LoRA Rank=8]
Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation
FedOPAL-W beats FedSA
0.850 vs 0.844
Balanced client test accuracy · [Camelyon17-WILDS task]
Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.