Federated Learning [Systems Design Sundays]
Even if you're not into Machine Learning, you should know this
To learn more about the newsletter, check our detailed About Page + FAQs
To help me understand you better, please fill out this anonymous, 2-min survey. If you liked this post, make sure you hit the heart icon in this email/post.
Before we begin, there is something I want to say to you,
Thank you. I just got the following email from Substack. This honestly feels unreal to me. Thank you so much for all the love and support.
With all the insanity that is a staple of life, it can be easy to forget that this newsletter, in its current state has only existed since Late March/Early April of this year. I ran a few tests prior to that, but this version is a relatively new thing. Thank you for being a part of this journey with me. I can promise you, there is a lot more to come. Now let’s get back to the lesson for today.
I want you to think about Amazon’s Alexa,
Or Google Assistant. YouTube. Instagram. Or any of the other applications that get multiple inputs from a single user every day. They also use information from other users for other input. They use these inputs to refine their algorithms and improve the user experience for all their users. We all know how it happens. They take the data and send it over to the servers. The servers apply fancy Machine Learning Algorithms and use that to send recommendations to all the different users.
This is how traditional ML has been implemented when designing systems. However, there are a few problems with this approach. One is the scale. This approach works for applications with small user bases and +updates. However, when things scale up, constantly sending data back to the servers will get very costly very quickly. Secondly, this data might contain sensitive information. If intercepted, this will cause a lot of probelms.
Federated learning avoids that. Here are the quick points on the principle behind Federated Learning-
What is it- Let’s take the system of Alexas. Each Alexa would have its own mini ML model that is trained based on its owner and input. The model can be updated with every input. These updates are then shared with the Amazon server, where a giant ML model is trained, using the updates of all the Alexa devices.
Why- Cheaper training, better security. Also from an ML perspective, you can do some cool things with this architecture. I will cover the Machine Learning aspect in more depth on my YouTube and Medium. Follow me there if you’re interested.
When could FL be a good solution- If you’re asked to design a dynamic system that is constantly changing based on user preferences, then FL can be a great solution. Especially if your learning process can be handled in a distributed manner (you have multiple simultaneous user input interfaces). Think any social media/recommendation system.
Since most of you aren’t going to be ML people, you don’t need to worry about the details. However, you should know about the protocol. Just being able to talk about it for 5 minutes at a high level will give you a huge leg up. And give you exposure to one of the most important AI concepts for the future. For an easy introduction to the topic, including how Google uses it, watch the 5 minute video below.
I hope you enjoyed the piece on Harish Mehta, NASSCOM, and India’s Tech Revolution yesterday. If you missed it, make sure you read it here. I put a lot of work into that, and so far all the readers have really learnt a lot from it.
I created Technology Interviews Made Simple using new techniques discovered through tutoring multiple people into top tech firms. The newsletter is designed to help you succeed, saving you from hours wasted on the Leetcode grind. I have a 100% satisfaction policy, so you can try it out at no risk to you. You can read the FAQs and find out more here. Use the button below to get 50% off for upto a whole year.
This is a limited-time offer, that I’m running to celebrate my almost 50 questions completed. Take advantage of it by clicking the button above.
If you have enjoyed this post so far, please make sure you like it (the little heart button in the email/post). I also have a special request for you.
***Special Request***
This newsletter has received a lot of love. If you haven’t already, I would really appreciate it if you could take 5 seconds to let Substack know that they should feature this publication on their pages. This will allow more people to see the newsletter.
There is a simple form in Substack that you can fill up for it. Here it is. Thank you.
https://docs.google.com/forms/d/e/1FAIpQLScs-yyToUvWUXIUuIfxz17dmZfzpNp5g7Gw7JUgzbFEhSxsvw/viewform
To get your Substack URL, follow the following steps-
Open - https://substack.com/
If you haven’t already, log in with your email.
In the top right corner, you will see your icon. Click on it. You will see the drop-down. Click on your name/profile. That will show you the link.
You will be redirected to your URL. Please put that in to the survey. Appreciate your help.
In the comments below, share what topic you want to focus on next. I’d be interested in learning and will cover them. To learn more about the newsletter, check our detailed About Page + FAQs
If you liked this post, make sure you fill out this survey. It’s anonymous and will take 2 minutes of your time. It will help me understand you better, allowing for better content.
https://forms.gle/XfTXSjnC8W2wR9qT9
I’ll see you living the dream.
Go kill all and Stay Woke,
Devansh <3
To make sure you get the most out of System Design Sundays, make sure you’re checking in the rest of the days as well. Leverage all the techniques I have discovered through my successful tutoring to easily succeed in your interviews and save your time and energy by joining the premium subscribers down below. Get a discount (for a whole year) using the button below
Reach out to me on:
Instagram: https://www.instagram.com/iseethings404/
Message me on Twitter: https://twitter.com/Machine01776819
My LinkedIn: https://www.linkedin.com/in/devansh-devansh-516004168/
My content:
Read my articles: https://rb.gy/zn1aiu
My YouTube: https://rb.gy/88iwdd
Get a free stock on Robinhood. No risk to you, so not using the link is losing free money: https://join.robinhood.com/fnud75