SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.02247 · 2026

Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning

Xinyi Shang, Yang Lu, Yiqun Zhang, Jiacheng Yang, Chikai Shang, Zhiheng Yang, Shihao Hou, Junlong Gao

arXiv · PDF · Open in the Atlas

Code that ran

10 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 4 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2605.02247.json · badge: /api/ran/2605.02247.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
shihaohou/FedPuReL canonical (classifier label)
classifier basis: census
10 ran · 4 no recorded run
FunctionStatusWhere it lives
calculate_accuracy_20 Ran
ran, honoured the contract we drafted
shihaohou/FedPuReL/federated_main.py
pointer only (licence: NONE) · get_code("4c579c5f6075265e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_class_proportions Ran
ran; our contract draft was wrong, not the code
shihaohou/FedPuReL/datasets/imagenet_LT.py
pointer only (licence: NONE) · get_code("0b7df800c2c5026e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_class_distribution Ran
ran; our contract draft was wrong, not the code
shihaohou/FedPuReL/datasets/imagenet_LT.py
pointer only (licence: NONE) · get_code("c297d34ca52d4765")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_lora_parameters Ran
ran; our contract draft was wrong, not the code
shihaohou/FedPuReL/loralib/utils.py
pointer only (licence: NONE) · get_code("3525af0b792c8af0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_pairs Ran
ran; our contract draft was wrong, not the code
shihaohou/FedPuReL/clip/simple_tokenizer.py
pointer only (licence: NONE) · get_code("d919ae32e5e4e616")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

lora_state_dict Ran
ran; our contract draft was wrong, not the code
shihaohou/FedPuReL/loralib/utils.py
pointer only (licence: NONE) · get_code("660073ae6862ac6e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_path Ran
ran; our contract draft was wrong, not the code
shihaohou/FedPuReL/datasets/imagenet_LT.py
pointer only (licence: NONE) · get_code("15e3cfc1c2d3a4e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

state_dict_to_cpu Ran
ran; our contract draft was wrong, not the code
shihaohou/FedPuReL/federated_main.py
pointer only (licence: NONE) · get_code("7f68a38128af9977")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

tensor_to_cpu Ran
ran, honoured the contract we drafted
shihaohou/FedPuReL/federated_main.py
pointer only (licence: NONE) · get_code("5176cecaa64a4319")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

whitespace_clean Ran
ran; our contract draft was wrong, not the code
shihaohou/FedPuReL/clip/simple_tokenizer.py
pointer only (licence: NONE); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_lora Not yet run
unverified (harvested, no recorded run)
shihaohou/FedPuReL/loralib/utils.py
pointer only (licence: NONE) · get_code("c97562384190aaf5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

build_model Not yet run
unverified (harvested, no recorded run)
shihaohou/FedPuReL/clip/model.py
pointer only (licence: NONE) · get_code("0d784ed171f1c8af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load Not yet run
unverified (harvested, no recorded run)
shihaohou/FedPuReL/clip/clip.py
pointer only (licence: NONE) · get_code("fbf8c0143d9c48e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

set_param Not yet run
unverified (harvested, no recorded run)
shihaohou/FedPuReL/loralib/layers.py
pointer only (licence: NONE); the stored copy get_code serves, from maxzanella/clip-lora, is pointer only (licence: AGPL-3.0) · get_code("e39f18623c2d033c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shihaohou/FedPuReL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 3 the same month, 4 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_pairs 258 other papers
248 dated earlier, 3 the same month, 6 later, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
whitespace_clean 231 other papers
223 dated earlier, 3 the same month, 4 later, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 228 more not named here
load 88 other papers
86 dated earlier, 1 later, 1 undated
2203.05557 (2022-03)
Conditional Prompt Learning for Vision-Language Models
2206.01986 (2022-06)
Delving into the Openness of CLIP
2207.12819 (2022-07)
S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning
and 85 more not named here
lora_state_dict 13 other papers
13 dated earlier
2202.00535 (2022-02)
Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning
2202.07962 (2022-02)
Revisiting Parameter-Efficient Tuning: Are We Really There Yet?
2211.09790 (2022-11)
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
and 10 more not named here
set_param 7 other papers
6 dated earlier, 1 the same month · 2 only as an assembly brick
2401.09257 (2024-01)
A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization
2405.18541 (2024-05)
Low-Rank Few-Shot Adaptation of Vision-Language Models
2501.10945 (2025-01)
Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond
and 4 more not named here
build_model 5 other papers
4 dated earlier, 1 later
2403.00041 (2024-03)
Global and Local Prompts Cooperation via Optimal Transport for Federated Learning
2405.09771 (2024-05)
Harmonizing Generalization and Personalization in Federated Prompt Learning
2409.19610 (2024-09)
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
and 2 more not named here
get_lora_parameters 1 other paper
1 dated earlier
2601.12493 (2026-01)
Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Personalized federated learning (PFL) with foundation models has emerged as a promising paradigm enabling clients to adapt to heterogeneous data distributions. However, real-world scenarios often face the co-occurrence of non-IID data and long-tailed class distributions, presenting unique challenges that remain underexplored in PFL. In this paper, we investigate this long-tailed personalized federated learning and observe that current methods suffer from two limitations: (i) Fine-tuning degrades performance below zero-shot baselines due to the erosion of inherent class balance in foundation models; (ii) Conventional personalization techniques further transfer this bias to local models through parameter or feature-level fusion. To address these challenges, we propose Federated Learning via Gradient Purification and Residual Learning (FedPuReL), which preserves balanced knowledge in the global model while enabling unbiased personalization. Specifically, we purify local gradients using zero-shot predictions to maintain a class-balanced global model, and model personalization as residual corrections atop the frozen global model. Extensive experiments demonstrate that FedPuReL consistently outperforms state-of-the-art methods, achieving superior performance on both global and personalized models across diverse long-tailed scenarios. The code is available at https://github.com/shihaohou/FedPuReL.

For agents

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

get_harvested_code_for_paper("2605.02247")
get_code_for_paper("2605.02247")
have("2605.02247")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2605.02247.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2605.02247.svg)](https://syntology.ai/paper/2605.02247)

Connect an agent — have() is free.