# C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning

arXiv: https://arxiv.org/abs/2411.00311 · HTML: https://mlsanity.com/paper/2411.00311/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 1 Nov 2024.

## Builds on (most cited first, 29 of 29)

- [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)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks](https://mlsanity.com/paper/2112.06825/) (2021)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2106.05001/) (2021)
- [XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation](https://mlsanity.com/paper/2004.01401/) (2020)
- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019)
- [Improving Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2104.00466/) (2021)
- [AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning](https://mlsanity.com/paper/2210.17451/) (2022)
- [What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning](https://mlsanity.com/paper/1911.03090/) (2019)
- [HyperPrompt: Prompt-based Task-Conditioning of Transformers](https://mlsanity.com/paper/2203.00759/) (2022)
- [How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations](https://mlsanity.com/paper/1909.04925/) (2019)
- [What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models](https://mlsanity.com/paper/2004.06499/) (2020)
- [Exploiting Adapters for Cross-lingual Low-resource Speech Recognition](https://mlsanity.com/paper/2105.11905/) (2021)
- [Federated Learning of N-gram Language Models](https://mlsanity.com/paper/1910.03432/) (2019)
- [Pretrained Models for Multilingual Federated Learning](https://mlsanity.com/paper/2206.02291/) (2022)
- [FedMatch: Federated Learning Over Heterogeneous Question Answering Data](https://mlsanity.com/paper/2108.05069/) (2021)
- [Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer](https://mlsanity.com/paper/2205.12148/) (2022)

## Built on by (most cited first, 8 of 8)

- [A Survey on Parameter-Efficient Fine-Tuning for Foundation Models in Federated Learning](https://mlsanity.com/paper/2504.21099/) (2025)
- [Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data](https://mlsanity.com/paper/2502.19752/) (2025)
- [FLoRIST: Singular Value Thresholding for Efficient and Accurate Federated Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2506.09199/) (2025)
- [Learning Like Humans: Resource-Efficient Federated Fine-Tuning through Cognitive Developmental Stages](https://mlsanity.com/paper/2508.00041/) (2025)
- [Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2506.04453/) (2025)
- [Assortment of Attention Heads: Accelerating Federated PEFT with Head Pruning and Strategic Client Selection](https://mlsanity.com/paper/2506.00743/) (2025)
- [FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE](https://mlsanity.com/paper/2506.16600/) (2025)
- [MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning](https://mlsanity.com/paper/2608.01521/) (2026)

## Abstract (arXiv)

Despite the versatility of pre-trained language models (PLMs) across domains, their large memory footprints pose significant challenges in federated learning (FL), where the training model has to be distributed between a server and clients. One potential solution to bypass such constraints might be the use of parameter-efficient fine-tuning (PEFT) in the context of FL. However, we have observed that typical PEFT tends to severely suffer from heterogeneity among clients in FL scenarios, resulting in unstable and slow convergence. In this paper, we propose Client-Customized Adaptation (C2A), a novel hypernetwork-based FL framework that generates client-specific adapters by conditioning the client information. With the effectiveness of the hypernetworks in generating customized weights through learning to adopt the different characteristics of inputs, C2A can maximize the utility of shared model parameters while minimizing the divergence caused by client heterogeneity. To verify the efficacy of C2A, we perform extensive evaluations on FL scenarios involving heterogeneity in label and language distributions. Comprehensive evaluation results clearly support the superiority of C2A in terms of both efficiency and effectiveness in FL scenarios.