Aayush Mudgal, Senior Machine Learning Engineer at Pinterest, discusses the evolution of ads ranking at Pinterest, including transitioning to deep learning-based transformer models. Topics covered include challenges in productionizing large language models, transitioning to deep learning models, incorporating sequential signals, multi-task learning, and transfer learning, scaling machine learning at Pinterest, and the use of transformers in ad rankings and recommendation models.
Read more
AI Summary
AI Chapters
Episode notes
auto_awesome
Podcast summary created with Snipd AI
Quick takeaways
Evaluate effort and potential gain before making design decisions.
Optimize data pipelines and implement monitoring and alerting systems.
Start with simpler solutions and gradually move towards more complex ones while considering trade-offs.
Deep dives
Evolution and decision making in a big company
The podcast episode explores the evolution process of ML projects in a big company, focusing on decision-making and the challenges faced in migrating from one technology to another. It highlights the importance of evaluating the effort and potential gain before making design decisions. It also emphasizes the need for commitment, top-down support, and building the right tooling for smooth migrations.
Improving pipelines and data preparation
The episode discusses the importance of optimizing pipelines and reducing intermediate steps in data preparation when training models. It mentions the benefits of having an efficient data pipeline and the need for monitoring and alerting systems to catch issues early on.
Migration challenges and language adoption
The podcast covers the challenges faced in migrating from one language or framework to another and the importance of having the right tooling and infrastructure in place. It also addresses the trade-offs between simplicity and complexity, highlighting the benefits of starting with simpler solutions and gradually moving towards more complex ones.
The use of transformers in recommendation systems
The episode explores the use of transformers, particularly in recommendation systems and ad rankings. It discusses how transformers can be used for feature interaction and sequence modeling in order to improve personalization. It also addresses the challenges of latency and optimization strategies to ensure fast and efficient serving of recommendations.
Balancing scale and performance in recommendation systems
The episode delves into the challenges of maintaining scale and performance in recommendation systems. It discusses the need for infrastructure optimizations, including GPU serving and strategy adjustments. It also touches on managing costs and finding the right balance between personalization and infrastructure requirements.
Aayush Mudgal is a Senior Machine Learning Engineer at Pinterest, currently leading the efforts around Privacy-Aware Conversion Modeling.
Large Language Models have taken the world by storm. But what are the real use cases? What are the challenges in productionizing them? In this event, you will hear from practitioners about how they are dealing with things such as cost optimization, latency requirements, trust of output, and debugging. You will also get the opportunity to join workshops that will teach you how to set up your use cases and skip over all the headaches.
Join the AI in Production Conference on February 15 and 22 here: https://home.mlops.community/home/events/ai-in-production-2024-02-15
________________________________________________________________________________________
MLOps podcast #211 with Aayush Mudgal, Senior Machine Learning Engineer at Pinterest, Ads Ranking Evolution at Pinterest.
// Abstract
Listen to the lessons from the journey of scaling ads ranking at Pinterest using innovative machine learning algorithms and innovation in the ML platform. Learn how they transitioned from traditional logistic regressions to deep learning-based transformer models, incorporating sequential signals, multi-task learning, and transfer learning. Discover the hurdles Pinterest overcame and the insights they gained in this talk, as Aayush shares the transformation of ads ranking at Pinterest and the lessons learned along the way. Discover how ML Platform evolution is crucial for algorithmic advancements.
// Bio
Aayush Mudgal is a Senior Machine Learning Engineer at Pinterest, currently leading the efforts around Privacy-Aware Conversion Modeling. He has a successful track record of starting and executing 0 to 1 projects, including conversion optimization, video ads ranking, landing page optimization, and evolving the ads ranking from GBDT to DNN stack. His expertise is in large-scale recommendation systems, personalization, and ads marketplaces. Before entering the industry, Aayush conducted research on intelligent tutoring systems, developing data-driven feedback to aid students in learning computer programming. He holds a Master's in Computer Science from Columbia University and a Bachelor of Technology in Computer Science from the Indian Institute of Technology Kanpur.
// MLOps Jobs board
https://mlops.pallet.xyz/jobs
// MLOps Swag/Merch
https://mlops-community.myshopify.com/
// Related Links
https://www.youtube.com/watch?v=MZVIxtsGzBg
https://www.youtube.com/watch?v=ffpPUr8Hg6U
--------------- ✌️Connect With Us ✌️ -------------
Join our slack community: https://go.mlops.community/slack
Follow us on Twitter: @mlopscommunity
Sign up for the next meetup: https://go.mlops.community/register
Catch all episodes, blogs, newsletters, and more: https://mlops.community/
Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/
Connect with Aayush on LinkedIn: https://www.linkedin.com/in/aayushmudgal/
Get the Snipd podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share & Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode