# No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier

arXiv: https://arxiv.org/abs/2303.10058 · HTML: https://mlsanity.com/paper/2303.10058/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 58 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Federated Learning for Internet of Things: A Comprehensive Survey](https://mlsanity.com/paper/2104.07914/) (2021)
- [No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2106.05001/) (2021)
- [A Geometric Analysis of Neural Collapse with Unconstrained Features](https://mlsanity.com/paper/2105.02375/) (2021)
- [Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges](https://mlsanity.com/paper/2009.13012/) (2020)
- [FedALA: Adaptive Local Aggregation for Personalized Federated Learning](https://mlsanity.com/paper/2212.01197/) (2022)
- [Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2302.03004/) (2023)
- [Federated Learning with Label Distribution Skew via Logits Calibration](https://mlsanity.com/paper/2209.00189/) (2022)
- [Extended Unconstrained Features Model for Exploring Deep Neural Collapse](https://mlsanity.com/paper/2202.08087/) (2022)
- [DENSE: Data-Free One-Shot Federated Learning](https://mlsanity.com/paper/2112.12371/) (2021)
- [Neural Collapse: A Review on Modelling Principles and Generalization](https://mlsanity.com/paper/2206.04041/) (2022)
- [Reliable Federated Learning for Mobile Networks](https://mlsanity.com/paper/1910.06837/) (2019)
- [An Unconstrained Layer-Peeled Perspective on Neural Collapse](https://mlsanity.com/paper/2110.02796/) (2021)
- [Imbalance Trouble: Revisiting Neural-Collapse Geometry](https://mlsanity.com/paper/2208.05512/) (2022)
- [Tackling Data Heterogeneity in Federated Learning with Class Prototypes](https://mlsanity.com/paper/2212.02758/) (2022)

## Built on by (most cited first, 30 of 55)

- [FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning](https://mlsanity.com/paper/2401.03230/) (2024)
- [Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model](https://mlsanity.com/paper/2305.13165/) (2023)
- [Linguistic Collapse: Neural Collapse in (Large) Language Models](https://mlsanity.com/paper/2405.17767/) (2024)
- [Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity](https://mlsanity.com/paper/2405.16585/) (2024)
- [FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models](https://mlsanity.com/paper/2406.04845/) (2024)
- [FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors](https://mlsanity.com/paper/2503.15842/) (2025)
- [Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models](https://mlsanity.com/paper/2406.10630/) (2024)
- [An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning](https://mlsanity.com/paper/2403.15760/) (2024)
- [Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?](https://mlsanity.com/paper/2405.14468/) (2024)
- [Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse](https://mlsanity.com/paper/2410.04887/) (2024)
- [FedImpro: Measuring and Improving Client Update in Federated Learning](https://mlsanity.com/paper/2402.07011/) (2024)
- [FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning](https://mlsanity.com/paper/2308.12532/) (2023)
- [Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse](https://mlsanity.com/paper/2405.05587/) (2024)
- [Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning](https://mlsanity.com/paper/2503.06457/) (2025)
- [FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion](https://mlsanity.com/paper/2410.20380/) (2024)
- [FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data](https://mlsanity.com/paper/2401.08977/) (2024)
- [Accelerating Heterogeneous Federated Learning with Closed-form Classifiers](https://mlsanity.com/paper/2406.01116/) (2024)
- [Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers](https://mlsanity.com/paper/2505.15239/) (2025)
- [PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning](https://mlsanity.com/paper/2310.09183/) (2023)
- [FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning](https://mlsanity.com/paper/2311.13267/) (2023)
- [Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors](https://mlsanity.com/paper/2402.01342/) (2024)
- [Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2407.06136/) (2024)
- [FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking](https://mlsanity.com/paper/2503.15111/) (2025)
- [Subgraph Federated Learning for Local Generalization](https://mlsanity.com/paper/2503.03995/) (2025)
- [FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learning](https://mlsanity.com/paper/2311.18559/) (2023)
- [You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data](https://mlsanity.com/paper/2503.06916/) (2025)
- [Pairwise Similarity Learning is SimPLE](https://mlsanity.com/paper/2310.09449/) (2023)
- [Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning](https://mlsanity.com/paper/2412.14326/) (2024)
- [Understanding Prompt Tuning for V-L Models Through the Lens of Neural Collapse](https://mlsanity.com/paper/2306.15955/) (2023)
- [FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning](https://mlsanity.com/paper/2406.02355/) (2024)

## Abstract (arXiv)

Data heterogeneity is an inherent challenge that hinders the performance of federated learning (FL). Recent studies have identified the biased classifiers of local models as the key bottleneck. Previous attempts have used classifier calibration after FL training, but this approach falls short in improving the poor feature representations caused by training-time classifier biases. Resolving the classifier bias dilemma in FL requires a full understanding of the mechanisms behind the classifier. Recent advances in neural collapse have shown that the classifiers and feature prototypes under perfect training scenarios collapse into an optimal structure called simplex equiangular tight frame (ETF). Building on this neural collapse insight, we propose a solution to the FL's classifier bias problem by utilizing a synthetic and fixed ETF classifier during training. The optimal classifier structure enables all clients to learn unified and optimal feature representations even under extremely heterogeneous data. We devise several effective modules to better adapt the ETF structure in FL, achieving both high generalization and personalization. Extensive experiments demonstrate that our method achieves state-of-the-art performances on CIFAR-10, CIFAR-100, and Tiny-ImageNet.