Federated Learning Research Topics

Federated learning is a branch of machine learning which focus mainly on data privacy and security of the user by storing it in local and without sharing it with any centralized device, along with it this can also provide collaboration with distant devices. Here by reading this paper you can learn more about it.

  1. Define Federated Learning

This is nothing but a technique of machine learning which is used to store the input of user privately in local while training one common model with the help of several dispersed devices or systems. The main objective of this is to maintain the privacy and security of the received data by checking the problem rose in the models which were trained by machine learning because it has numerous data collected from different devices and this is not done using centralization of all data in one particular location.

  1. What is Federated Learning?

It is one of the machine learning techniques, which focuses mainly on the privacy and security of data which is stored in local along with training a model with the help of several devices. This is done by analyzing the issues from the trained model which receives data from various places without centralizing one location for all data.

  1. Where Federated Learning is used?

Federated learning is implemented in the field which keeps privacy and security as their top priority. The scenarios where federated learning is used commonly are listed further: In the fields of Mobile device, Autonomous vehicles, Industrial and manufacture, Retail, Financial services, Internet of things (IoT), Healthcare, Edge device, Federated search and Agriculture.

  1. Why Federated Learning is proposed? Previous Technology Issues

The IoT devices can keep their data’s securely with the help of federated learning to identify the insider threat while maintaining the privacy of data and following the regulations. By making use of this strategy a business can easily identify and reduce the insider threats also able to keep their information confidentially with maintaining the regulations for data protection. This learning technique was proposed in order to address various issues, in which some of them are: Data security and privacy, Resource limitation, Infrastructure and Compatibility and Communication overhead.

  1. Algorithms / Protocols

The algorithms provided for Federated learning to overcome the previous issues faced by it are: “Multi-key Homomorphic encryption protocol” (xMK-CKKS), “Hierarchical Federated learning-based Intrusion Detection systems” (HFed-IDS), “Chirp Spread Spectrum”, “K-nearest neighbor and neural network” (KNN-NN), “Transformer-based intrusion detection model” (Transformer-IDM), “Markov Decision Process” (MDP), “Carrier Frequency Offset and Multilayer perceptron” (MLP) and “Auto encoder neural network”.

  1. Comparative study / Analysis

The analysis of this study is done based on the Accuracy, Thresholds, True negative rate, True positive rate, Recall, Detection rate, Precision, Behavioral analysis and F1-score.

  1. Simulation results / Parameters

The approaches which were proposed to overcome the issues faced by Federated learning are tested using different methodologies to analyze its performance. The comparison is done by using metrics like Time period vs. trust value, Node number vs. batch size, Accuracy vs. Communication rounds, Accuracy vs. number of IoT devices, Performance vs. tests, Throughput vs. running time.

  1. Dataset LINKS / Important URL

Here are some of the links provided for you below to gain more knowledge about Federated learning which can be useful for you:

  1. Federated Learning Applications

This is mostly used in the field where privacy is more important without sharing the data along with collaboration of machine learning. It is used in the healthcare industry for hospitals which collaborate with training the model and protect privacy of the patients which is necessary for identifying the disease and optimizing treatment for it. Also used in collaboration with banks to detect the fraud algorithm by keeping the client data private, this can occur in financial sector. Gadgets and smartphones use federated learning to maintain privacy of user by not sharing the raw data with any central servers. It can also be used in the situations of edge computing, which increases AI models with decreasing data transport in dispersed devices.

  1. Topology

The commonly used topology for Federated learning is the topology called Decentralized network. This uses many nodes or edge devices such as devices with Internet of Things or smartphones which stores data in local dataset and controlled by any central server. The update for each node will be received from the central server and changes done in the nodes are saved in the local storage. Those updates in the local will make the model enhanced with the help of combining all changes which is done by the central server with maintaining privacy for information. The advantages of this topology are privacy, data transfer in large scale, unreliable and collaboration with machine learning.

  1. Environment

The environment which is suitable for Federated learning is the fields which require more privacy as well as security for keeping their data, such as finance and healthcare industry.

  1. Simulation Tools

Here we provide some simulation software for previous works, which is established with the usage of python software with version 3.11.4

  1. Results

After going through this research on Federated learning, you can understand in detail about this technology, applications of this technology, different topologies of it, algorithms followed by it. You can also know about the reason behind proposing of this technology.

Federated Learning Research Ideas

  1. APPFLx: Providing Privacy-Preserving Cross-Silo Federated Learning as a Service
  2. A Federated Learning Framework Based on CSP Homomorphic Encryption
  3. Federated learning: Applications, Security hazards and Defense measures
  4. Comparison of Federated Learning Algorithms for Image Classification
  5. Computation-Effective Personalized Federated Learning: A Meta Learning Approach
  6. Privacy-Preserving Anomaly Detection in Smart Meter Data via Federated Learning
  7. Learning across Decentralized Multi-Modal Remote Sensing Archives with Federated Learning
  8. Federated Learning for Distributed NWDAF Architecture
  9. Privacy-Preserving On-Screen Activity Tracking and Classification in E-Learning Using Federated Learning
  10. Research on Model Optimization Technology of Federated Learning
  11. Balancing Federated Learning Trade-Offs for Heterogeneous Environments
  12. FedDHr: Improved Adaptive Learning Strategy Using Federated Learning for Image Processing
  13. Adaptive Edge-Level Personalization on Hierarchical Federated Learning
  14. Federated Learning for Beginners: Types, Simulation Environments, and Open Challenges
  15. Federated Learning-assisted Self-supervised CNN for Monkey pox Diagnosis
  16. Federated Learning Methods for Analytics of Big and Sensitive Distributed Data and Survey
  17. Secured Data Sharing of Medical Images for Disease diagnosis using Deep Learning Models and Federated Learning Framework
  18. Integration of Federated Learning and Blockchain for the Provision of Secure Big data Analytics: Systematic Literature Review
  19. Implementation of Secure and Privacy-aware AI Hardware using Distributed Federated Learning
  20. Healthcare Diagnostics Service Using Federated Learning
  21. Dynamic Fair Federated Learning Based on Reinforcement Learning
  22. QuaFedAsync: Quality-based Asynchronous Federated Learning for the Embedded Systems
  23. Federated Learning Algorithm Handling Missing Attributes
  24. Comparison of Federated Learning Strategies on ECG Classification
  25. Comparison of Multi-Modal Federated Learning Framework and SPSS in the Evaluation of Lymph Node Metastasis Probability in Gynecological Malignancies
  26. Proof-of-Federated-Learning-Subchain: Free Partner Selection Subchain Based on Federated Learning
  27. A Collaboration Federated Learning Framework with a Grouping Scheme against Poisoning Attacks
  28. F2MKD: Fog-enabled Federated Learning with Mutual Knowledge Distillation
  29. SGFL: A Federated Learning Approach for Non-IID Data Using Semi-Supervised DCGAN
  30. Incentive Based Federated Learning Data Dissemination for Vehicular Edge Computing Networks
  31. The Effect of Hyper-parameters in Model-contrastive Federated Learning Algorithm
  32. Boulez: A Chatbot-Based Federated Learning System for Distance Learning
  33. Networked Personalized Federated Learning Using Reinforcement Learning
  34. Reliable and Interpretable Personalized Federated Learning
  35. A Beginner’s Guide to Federated Learning
  36. Effectiveness of Model and Data Scale Contrastive Learning in Non-IID Federated Learning
  37. Federated Learning to Preserve the Privacy of User Data
  38. Federated Learning and Genetic Mutation for Multi-Resident Activity Recognition
  39. DEFL: A Novel Blockchain Fully-Orchestrated Federated Learning Framework
  40. Privacy-preserving continuous learning for MobileSAM via Federated Learning
  41. FedAvg-DWA: A Novel Algorithm for Enhanced Fraud Detection in Federated Learning Environment
  42. A Network Traffic Classification Method Based on Federated Learning and Extreme Learning Machine
  43. Advancing Security and Efficiency in Federated Learning Service Aggregation for Wireless Networks
  44. Enhanced COVID-19 Detection and Privacy Preserving Using Federated Learning
  45. Spectrum Occupancy Detection Supported by Federated Learning
  46. Federated Learning Technology in Serial Topology for IoT Networks
  47. Vertical Federated Learning in Malware Detection for Smart Cities
  48. Dynamic Spectrum Sharing Based on Federated Learning and Multi-Agent Actor-Critic Reinforcement Learning
  49. Federated Learning Model for Early Detection of Dementia Using Blood Biosamples
  50. A Cloud-Native Federated Learning Architecture for Telecom Fraud Detection
Opening Time


Lunch Time


Break Time


Closing Time


  • award1
  • award2