# Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning

arXiv: https://arxiv.org/abs/2304.04326 · HTML: https://mlsanity.com/paper/2304.04326/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Federated, robust and private distillation, one of 12 directions in Knowledge distillation.
- Builds on 38 of its 54 references that are in the map.
- First posted on arXiv 9 Apr 2023.

## Placed in

- Knowledge distillation / [Federated, robust and private distillation](https://mlsanity.com/distill/federated-robust-and-private-distillation/)

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [The Non-IID Data Quagmire of Decentralized Machine Learning](https://mlsanity.com/paper/1910.00189/) (2019)
- [Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data](https://mlsanity.com/paper/1811.11479/) (2018)
- [Asynchronous Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1710.06952/) (2017)
- [Stochastic Gradient Push for Distributed Deep Learning](https://mlsanity.com/paper/1811.10792/) (2018)
- [D2: Decentralized Training over Decentralized Data](https://mlsanity.com/paper/1803.07068/) (2018)
- [Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data](https://mlsanity.com/paper/2008.06180/) (2020)
- [Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization](https://mlsanity.com/paper/1709.08765/) (2017)
- [Convergence of Edge Computing and Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/1907.08349/) (2019)
- [Decentralized Deep Learning with Arbitrary Communication Compression](https://mlsanity.com/paper/1907.09356/) (2019)
- [Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data](https://mlsanity.com/paper/2102.04761/) (2021)
- [An Improved Analysis of Gradient Tracking for Decentralized Machine Learning](https://mlsanity.com/paper/2202.03836/) (2022)
- [Siloed Federated Learning for Multi-Centric Histopathology Datasets](https://mlsanity.com/paper/2008.07424/) (2020)
- [Consensus Control for Decentralized Deep Learning](https://mlsanity.com/paper/2102.04828/) (2021)
- [Evolving Normalization-Activation Layers](https://mlsanity.com/paper/2004.02967/) (2020)

## Built on by (most cited first, 3 of 3)

- [Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data](https://mlsanity.com/paper/2310.15890/) (2023)
- [Topology-Aware Knowledge Propagation in Decentralized Learning](https://mlsanity.com/paper/2505.11760/) (2025)
- [Learned Neighbor Trust for Collaborative Deployment in Model-Agnostic Decentralized Learning](https://mlsanity.com/paper/2605.05009/) (2026)

## Abstract (arXiv)

Decentralized learning enables serverless training of deep neural networks (DNNs) in a distributed manner on multiple nodes. This allows for the use of large datasets, as well as the ability to train with a wide variety of data sources. However, one of the key challenges with decentralized learning is heterogeneity in the data distribution across the nodes. In this paper, we propose In-Distribution Knowledge Distillation (IDKD) to address the challenge of heterogeneous data distribution. The goal of IDKD is to homogenize the data distribution across the nodes. While such data homogenization can be achieved by exchanging data among the nodes sacrificing privacy, IDKD achieves the same objective using a common public dataset across nodes without breaking the privacy constraint. This public dataset is different from the training dataset and is used to distill the knowledge from each node and communicate it to its neighbors through the generated labels. With traditional knowledge distillation, the generalization of the distilled model is reduced because all the public dataset samples are used irrespective of their similarity to the local dataset. Thus, we introduce an Out-of-Distribution (OoD) detector at each node to label a subset of the public dataset that maps close to the local training data distribution. Finally, only labels corresponding to these subsets are exchanged among the nodes and with appropriate label averaging each node is finetuned on these data subsets along with its local data. Our experiments on multiple image classification datasets and graph topologies show that the proposed IDKD scheme is more effective than traditional knowledge distillation and achieves state-of-the-art generalization performance on heterogeneously distributed data with minimal communication overhead.