AIMultiple ResearchAIMultiple Research

What is Federated Learning? Use Cases & Benefits in 2024

From customer service chatbots to making predictions and informing decision-making, AI and ML algorithms are being used in a wide range of business applications.

However, in order for AI models to be effective, they often require large amounts of data to be trained on. This can be a problem for businesses that handle sensitive customer or proprietary data, as they may be hesitant to share this data with third parties or even with other departments within the same organization.

Federated learning is a machine learning technique that enables organizations to train AI models on decentralized data, without the need to centralize or share that data. This means businesses can use AI to make better decisions without sacrificing data privacy and risking breaching personal information.

In this article, we’ll explore what federated learning is, how it works, its importance for businesses, and its common use cases and benefits.

What is federated learning?

Federated learning is used to train other machine learning algorithms by using multiple local datasets without exchanging data. This allows companies to create a shared global model without putting training data in a central location.

How does it work?

In machine learning, there are 2 steps, training and inference.

During training:

  1. Local machine learning (ML) models are trained on local heterogeneous datasets. For example, as users use a machine learning application, they spot mistakes in the machine learning application’s predictions and correct those mistakes. These create local training datasets in each user’s device.
  2. The parameters of the models are exchanged between these local data centers periodically. In many models, these parameters are encrypted before exchanging. Local data samples are not shared. This improves data protection and cybersecurity.
  3. A shared global model is built.
  4. The characteristics of the global model are shared with local data centers to integrate the global model into their ML local models.

For example, Nvidia’s Clara solution includes federated learning. Clara and Nvidia EGX allow learnings (but not training data) from different sites to be securely collected. This helps models to set up a global model while preserving data privacy.

NVIDIA demonstrates how federated learning works.
Source: NVIDIA

In inference, the model is stored on the user device so predictions are quickly prepared using the model on the user device.

Why is it important now?

Accurate machine learning models are valuable to companies and traditional centralized machine learning approaches have shortcomings like lack of continual learning on edge devices and aggregating private data on central servers. These are alleviated by federated learning.

In traditional machine learning, a central ML model is built using all available training data in a centralized environment. This works without any issues when a central server can serve the predictions.

However, in mobile computing, users demand fast responses and the communication time between the user device and a central server may be too slow for a good user experience. To overcome this, the model may be placed in the end-user device but then continual learning becomes a challenge since models are trained on a complete data set and the end user device does not have access to the complete dataset.

Another challenge with traditional machine learning is that user’s data gets aggregated in a central location for machine learning training which may be against the privacy policies of certain countries and may make the data more vulnerable to data breaches

Federated learning overcomes these challenges by enabling continual learning on end-user devices while ensuring that end user data does not leave end-user devices.

What is the level of interest in federated learning?

Federated learning is a new research topic in the machine learning domain. Interest in federated learning increased after studies especially in the telecommunications field in 2015. A Google AI post in 2017 further increased interest as can be seen from the graphic below. Most likely federated learning will be an active research topic. Studies on federated learning can expand depending on the need for advanced new learning processes/architectures in the machine learning domain.

Interest in federated learning according to Google Trends
Source: Google Trends

What are potential use cases and examples of federated learning?

Federated learning models can work with different machine learning techniques but data type and context are important. Potential applications may be learning activities of mobile phone users, autonomous vehicles and foreseeing health risks from wearable devices.

Mobile applications

Federated learning can be used to build models on user behavior from a data pool of smart phones without leaking personal data, such as for next-word prediction, face detection, voice recognition, etc. For example, Google uses federated learning to improve on-device machine learning models like “Hey Google” in Google Assistant which allows users to issue voice commands.

Healthcare

Healthcare and health insurance industry can take advantage of federated learning because it allows protecting sensitive data in the original source. Federated learning models can provide better data diversity by gathering data from various locations (e.g. hospitals, electronic health record databases) to diagnose rare diseases.

A new study, “The future of digital health with federated learning”, claims that federated learning can help to solve challenges about data privacy and data governance by enabling machine learning models from non-co-located data.

Autonomous Vehicles

Federated learning can provide a better and safer self-driving car experience with real-time data and predictions. Autonomous vehicles need these to respond to new situations:

  • real-time information about the traffic and roads
  • real-time decision making
  • continual learning

Federated learning can achieve all of these objectives and allow the models to improve over time with input from different vehicles. For example, a research project has demonstrated that federated learning can reduce training time in wheel steering angle prediction in self-driving vehicles.

Manufacturing – predictive maintenance

Manufacturing companies can use federated learning models to develop predictive maintenance models for equipment. Predictive maintenance can face some barriers such as customers who do not want to share their personal data or exporting data problems from different countries/sites. Federated learning can handle these challenges by using local datasets.

What are the benefits of federated learning?

Federated learning is an emerging area in the machine learning domain and it already provides significant benefits over traditional, centralized machine learning approaches. The benefits of federated learning are

  • Data security: Keeping the training dataset on the devices, so a data pool is not required for the model.
  • Data diversity: Challenges other than data security such as network unavailability in edge devices may prevent companies from merging datasets from different sources. Federated learning facilitates access to heterogeneous data even in cases where data sources can communicate only during certain times
  • Real-time continual learning: Models are constantly improved using client data with no need to aggregate data for continual learning.
  • Hardware efficiency: This approach uses less complex hardware, because federated learning models do not need one complex central server to analyze data

What are the challenges of federated learning?

  • Investment requirements: Federated learning models may require frequent communication between nodes. This means storage capacity and high bandwidth are among the system requirements.
  • Data Privacy:
  • Performance limitations:
    • Data heterogeneity: Models from diverse devices are merged to build a better model in federated learning. Device-specific characteristics may limit the generalization of the models from some devices and may reduce the accuracy of the next version of the model.
    • Indirect information leakage: Researchers have considered situations where one of the members of the federation can maliciously attack others by inserting hidden backdoors into the joint global model.
    • Federated learning is a relatively new machine learning procedure. New studies and research are required to improve its performance.
  • Centralization: There is still a degree of centralization in federated learning where a central model uses the output of other devices to build a new model. Researchers propose using blockchained federated learning (BlockFL) and other approaches to build zero-trust models of federated learning.

What are alternatives for federated learning?

Gossip learning had been proposed to address the same problem of training data privacy. This approach is fully decentralized and there is no server for merging outputs from different locations. Local nodes directly exchange and aggregate models. The advantage of gossip learning is its even less infrastructure and centralization requirements compared to federated learning. Gossip learning is a novel approach and further research is required to improve its performance and stability.

If you need help in choosing vendors for federated learning or other ML solutions that can help you get started, let us know:

Find the Right Vendors
Access Cem's 2 decades of B2B tech experience as a tech consultant, enterprise leader, startup entrepreneur & industry analyst. Leverage insights informing top Fortune 500 every month.
Cem Dilmegani
Principal Analyst
Follow on

Cem Dilmegani
Principal Analyst

Cem has been the principal analyst at AIMultiple since 2017. AIMultiple informs hundreds of thousands of businesses (as per similarWeb) including 60% of Fortune 500 every month.

Cem's work has been cited by leading global publications including Business Insider, Forbes, Washington Post, global firms like Deloitte, HPE, NGOs like World Economic Forum and supranational organizations like European Commission. You can see more reputable companies and media that referenced AIMultiple.

Throughout his career, Cem served as a tech consultant, tech buyer and tech entrepreneur. He advised businesses on their enterprise software, automation, cloud, AI / ML and other technology related decisions at McKinsey & Company and Altman Solon for more than a decade. He also published a McKinsey report on digitalization.

He led technology strategy and procurement of a telco while reporting to the CEO. He has also led commercial growth of deep tech company Hypatos that reached a 7 digit annual recurring revenue and a 9 digit valuation from 0 within 2 years. Cem's work in Hypatos was covered by leading technology publications like TechCrunch and Business Insider.

Cem regularly speaks at international technology conferences. He graduated from Bogazici University as a computer engineer and holds an MBA from Columbia Business School.

To stay up-to-date on B2B tech & accelerate your enterprise:

Follow on

Next to Read

Comments

Your email address will not be published. All fields are required.

0 Comments