# When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity

arXiv: https://arxiv.org/abs/2605.08992 · HTML: https://mlsanity.com/paper/2605.08992/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 9 May 2026.

## Builds on (most cited first, 14 of 14)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks](https://mlsanity.com/paper/2104.08815/) (2021)
- [A Survey on Efficient Federated Learning Methods for Foundation Model Training](https://mlsanity.com/paper/2401.04472/) (2024)
- [Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions](https://mlsanity.com/paper/2411.12377/) (2024)

## Built on by (most cited first, 1 of 1)

- [Perplexity Predicts Protection: Choosing Pretrained Backbones for Worst-Client Fairness in Federated Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2609.23463/) (2026)

## Abstract (arXiv)

Federated learning (FL) is increasingly used to fine-tune foundation models (FMs) on distributed private data. The community largely assumes that large-scale pretraining serves as a 'rising tide that lifts all boats' in federated settings. However, our experiments reveal that these powerful priors can hinder rather than help the most disadvantaged clients under extreme heterogeneity. Through controlled experiments on federated text classification, we compare worst-client accuracy between TextCNN (2.7M parameters) and DistilBERT with Low-Rank Adaptation (LoRA, 66M parameters) across four Non-IID heterogeneity levels. Under extreme label skew (alpha = 0.1), DistilBERT+LoRA produces a worst-client accuracy gap of 50.1% -- 56% larger than TextCNN's 32.2% gap, despite having 25x more parameters and extensive pretraining. Under moderate heterogeneity (alpha >= 0.5), the pattern reverses: the FM nearly eliminates the gap. We call this the FM Fairness Paradox. We further show that an inverse-weighted LoRA aggregation method (FedAvgW) does not resolve the disparity, suggesting aggregation reweighting alone may be insufficient. Our results highlight the need for mechanisms that explicitly protect minority clients before deploying foundation models in high-stakes federated contexts such as healthcare and education.