# Decentralized Federated Learning Preserves Model and Data Privacy

arXiv: https://arxiv.org/abs/2102.00880 · HTML: https://mlsanity.com/paper/2102.00880/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Builds on (most cited first, 12 of 12)

- [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)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Federated Machine Learning: Concept and Applications](https://mlsanity.com/paper/1902.04885/) (2019)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Practical Secure Aggregation for Federated Learning on User-Held Data](https://mlsanity.com/paper/1611.04482/) (2016)
- [D"IoT: A Federated Self-learning Anomaly Detection System for IoT](https://mlsanity.com/paper/1804.07474/) (2018)
- [Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach](https://mlsanity.com/paper/2007.09712/) (2020)
- [Self-Supervised Log Parsing](https://mlsanity.com/paper/2003.07905/) (2020)
- [Superiority of Simplicity: A Lightweight Model for Network Device Workload Prediction](https://mlsanity.com/paper/2007.03568/) (2020)

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

- [Federated Quantum Machine Learning](https://mlsanity.com/paper/2103.12010/) (2021)
- [Distributed Deep Learning in Open Collaborations](https://mlsanity.com/paper/2106.10207/) (2021)
- [Decentralized Federated Learning through Proxy Model Sharing](https://mlsanity.com/paper/2111.11343/) (2021)
- [A2Log: Attentive Augmented Log Anomaly Detection](https://mlsanity.com/paper/2109.09537/) (2021)
- [LogLAB: Attention-Based Labeling of Log Data Anomalies via Weak Supervision](https://mlsanity.com/paper/2111.01657/) (2021)
- [Federated and Transfer Learning for Cancer Detection Based on Image Analysis](https://mlsanity.com/paper/2405.20126/) (2024)
- [Dynamic Topology Optimization for Non-IID Data in Decentralized Learning](https://mlsanity.com/paper/2602.03383/) (2026)
- [Convergent Differential Privacy Analysis for General Federated Learning](https://mlsanity.com/paper/2408.15621/) (2024)

## Abstract (arXiv)

The increasing complexity of IT systems requires solutions, that support operations in case of failure. Therefore, Artificial Intelligence for System Operations (AIOps) is a field of research that is becoming increasingly focused, both in academia and industry. One of the major issues of this area is the lack of access to adequately labeled data, which is majorly due to legal protection regulations or industrial confidentiality. Methods to mitigate this stir from the area of federated learning, whereby no direct access to training data is required. Original approaches utilize a central instance to perform the model synchronization by periodical aggregation of all model parameters. However, there are many scenarios where trained models cannot be published since its either confidential knowledge or training data could be reconstructed from them. Furthermore the central instance needs to be trusted and is a single point of failure. As a solution, we propose a fully decentralized approach, which allows to share knowledge between trained models. Neither original training data nor model parameters need to be transmitted. The concept relies on teacher and student roles that are assigned to the models, whereby students are trained on the output of their teachers via synthetically generated input data. We conduct a case study on log anomaly detection. The results show that an untrained student model, trained on the teachers output reaches comparable F1-scores as the teacher. In addition, we demonstrate that our method allows the synchronization of several models trained on different distinct training data subsets.