# Concept-aware clustering for decentralized deep learning under temporal shift

arXiv: https://arxiv.org/abs/2306.12768 · HTML: https://mlsanity.com/paper/2306.12768/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 22 Jun 2023.

## Builds on (most cited first, 9 of 9)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Federated Machine Learning: Concept and Applications](https://mlsanity.com/paper/1902.04885/) (2019)
- [Federated Learning under Distributed Concept Drift](https://mlsanity.com/paper/2206.00799/) (2022)
- [Gossip training for deep learning](https://mlsanity.com/paper/1611.09726/) (2016)
- [Decentralized federated learning of deep neural networks on non-iid data](https://mlsanity.com/paper/2107.08517/) (2021)
- [Decentralized adaptive clustering of deep nets is beneficial for client collaboration](https://mlsanity.com/paper/2206.08839/) (2022)

## Abstract (arXiv)

Decentralized deep learning requires dealing with non-iid data across clients, which may also change over time due to temporal shifts. While non-iid data has been extensively studied in distributed settings, temporal shifts have received no attention. To the best of our knowledge, we are first with tackling the novel and challenging problem of decentralized learning with non-iid and dynamic data. We propose a novel algorithm that can automatically discover and adapt to the evolving concepts in the network, without any prior knowledge or estimation of the number of concepts. We evaluate our algorithm on standard benchmark datasets and demonstrate that it outperforms previous methods for decentralized learning.