Implementing Federated Learning to enhance Agentic AI

SPEAKER_1 (0:02)

Welcome to the Practical AI Podcast, where we break down the real world applications of artificial intelligence and how it's shaping the way we live, work and create. Our goal is to help make AI technology practical, productive and accessible to everyone. Whether you're a developer, business leader, or just curious about the tech behind the buzz, you're in the right place.

Be sure to connect with us on LinkedIn, X or Blue Sky to stay up to date with episode drops, behind the scenes content, and AI insights. You can learn more at practicalai.fm. Now, on to the show.

Chris Benson (0:41)

Welcome to another episode of the Practical AI podcast. I am Chris Benson, your co-host. Daniel Whitenack is out on paternity leave right now, so he won't be joining us. We've got a good conversation coming up today, I know, because with us, we have Lorenzo Sani, if I got your name correct there.

And Lorenzo is a research scientist at Flower Labs. He is also finishing up his PhD at Cambridge in computer science. Welcome to the show.

Lorenzo Sani (1:09)

Hello, Chris. Hello, everybody. Thanks for having me today.

Chris Benson (1:12)

Hey, absolutely. You have a really interesting set of research that you're working on. We're delighted to have you on the show today. I'm looking forward to talking about it. We've got a lot of questions about it.

But I wanted to actually start off with the fact that a little bit about your background. I know you came from the physics world and moved over, and we've seen that a fair amount in research scientists and AI. Daniel, the co-host who's not here today, is in the same boat. I'm just curious if you could give us a quick how you arrived at what you're doing now having started on the physics side of things.

Lorenzo Sani (1:50)

Yeah, of course. You're right. I have a physics background. I've been studying physics for five years after my high school. I was in Bologna, amazing place, amazing people and very good courses as well. Especially during my last year of masters, I was looking into topics related to machine learning, and the group there was working on medical applications. We needed a way to preserve privacy and looking into those privacy-sensitive scenarios. Back then, federated learning was quite new, so I started looking into it. It was very interesting. I love the motivations behind it and the way to carry along the privacy preserving component to it. As a result, I was one of the very first user of the Flower Framework, and this brought me to meet all the Flower people, as well as the research group in Cambridge that was developing it.

And things got along. Luckily enough, the professor, Nic Lane, here, was looking for PhD students. I was very excited to join this line of research and whatever was around it.

And I got lucky. I got a seat. I started working with the team. I started developing my own applications and methods. And over the course of the last few years, I got more familiar with the latest advancements of AI. I would say like these LLMs and everything related to it. Now, I can say I'm very familiar with everything that goes from collecting the data down to serving the models and using them day to day.

Chris Benson (3:29)

Can you talk a little bit about, as you dived into those areas, what were some of the specifics that really drew you in? What were some of the first problems that you addressed that kind of got you started in the area? And what drove the passion regarding that?

Lorenzo Sani (3:49)

Yeah, it's a very good question. I've thought a lot about this after a couple of years that I took this path, because I wanted just to go back and try to understand better my choices and why did I take them.

I think the main reason was related to the complexity behind this technology, because back when I decided to do physics, complexity was the most fascinating thing. It's about like studying physics and getting to know the world. And for this technology, it's mostly about we have a lot of data. We want to make sure that we have good machine learning technologies to learn from this data and get useful stuff done. But this data is very complex and the training procedures are very complex. So these things excite me a lot. In the Federated Learning kind of area, the complexity goes into the distribution itself because you have all these siloed data. It's very scattered, very heterogeneous, very difficult to deal with in the standard way.

But Federated Learning provides a good way to train, to train on this and get the intelligence that you want. It's similar to the direction I took when I started my PhD for the LLM pre-training stuff that I've done.