What are the key takeaways from this Software Engineering Daily episode?

Key insights include: **Relational Deep Learning Architecture:** Treat any enterprise relational database as a graph where tables are nodes and foreign key relationships are edges, then apply graph transformer attention mechanisms across this structure. This eliminates the need to manually join tables or pre-define SQL aggregations before training, letting the model learn which data combinations matter for a given prediction task.; **Foundation Model for Tabular Data (Kumo RFM):** A single pre-trained foundation model can connect to any structured database schema and answer predictive queries without task-specific retraining. Users define predictions using a structured "predictive query" language — for example, specifying churn as zero transactions in the next 30 days — and the frozen model fetches relevant subgraphs and returns probability scores on demand.; **Feature Engineering Cost Reduction:** Traditional predictive modeling requires approximately two full-time data scientists per production model, making 10 simultaneous models a 20-person commitment. Relational deep learning eliminates manual feature engineering by attending directly over raw database rows, columns, and linked tables, compressing that multi-person effort into a single reusable model infrastructure.

What did Jura Leskiewicz discuss on Software Engineering Daily?

Stanford professor Jure Leskovec and Kumo AI co-founder explains how relational deep learning applies transformer-based graph attention mechanisms directly to structured enterprise database tables, enabling foundation models that generate fraud detection, churn prediction, and recommendation outputs without manual feature engineering. Key topics include: **Relational Deep Learning Architecture:** Treat any enterprise relational database as a graph where tables are nodes and foreign key relationships are edges, then apply graph transformer attention mechanisms across this structure. This eliminates the need to manually join tables or pre-define SQL aggregations before training, letting the model learn which data combinations matter for a given prediction task.; **Foundation Model for Tabular Data (Kumo RFM):** A single pre-trained foundation model can connect to any structured database schema and answer predictive queries without task-specific retraining. Users define predictions using a structured "predictive query" language — for example, specifying churn as zero transactions in the next 30 days — and the frozen model fetches relevant subgraphs and returns probability scores on demand..

How long is this episode of Software Engineering Daily?

This episode is 44 minutes long. SignalCast provides an AI-generated summary so you can get the key insights in about 3 minutes.

Software Engineering Daily

Foundation Models for Structured Data

June 23, 2026

44 min episode · 2 min read

Jura Leskiewicz

Episode

44 min

Read time

2 min

Topics

Productivity, Relationships, Startups

AI-Generated Summary

Published Jun 23, 2026

Key Takeaways

✓Relational Deep Learning Architecture: Treat any enterprise relational database as a graph where tables are nodes and foreign key relationships are edges, then apply graph transformer attention mechanisms across this structure. This eliminates the need to manually join tables or pre-define SQL aggregations before training, letting the model learn which data combinations matter for a given prediction task.
✓Foundation Model for Tabular Data (Kumo RFM): A single pre-trained foundation model can connect to any structured database schema and answer predictive queries without task-specific retraining. Users define predictions using a structured "predictive query" language — for example, specifying churn as zero transactions in the next 30 days — and the frozen model fetches relevant subgraphs and returns probability scores on demand.
✓Feature Engineering Cost Reduction: Traditional predictive modeling requires approximately two full-time data scientists per production model, making 10 simultaneous models a 20-person commitment. Relational deep learning eliminates manual feature engineering by attending directly over raw database rows, columns, and linked tables, compressing that multi-person effort into a single reusable model infrastructure.
✓Model Size and Inference Efficiency: Relational deep learning models operate below one billion parameters, significantly smaller than large language models, enabling faster and cheaper inference. However, they require a specialized graph engine backend that optimizes database representations into graph form and supports subgraph sampling at scale across tens to hundreds of billions of nodes and edges.
✓Synthetic Pre-Training Data via Plural Method: A Stanford research paper called Plural demonstrates that synthetic structured tabular data can be generated at scale to pre-train relational foundation models, solving the data scarcity problem that would otherwise limit training. For high-throughput production use cases like real-time fraud scoring at millions of transactions per second, fine-tuning a smaller distilled version of the pre-trained model delivers speed and cost efficiency.

What It Covers

Stanford professor Jure Leskovec and Kumo AI co-founder explains how relational deep learning applies transformer-based graph attention mechanisms directly to structured enterprise database tables, enabling foundation models that generate fraud detection, churn prediction, and recommendation outputs without manual feature engineering.

Key Questions Answered

•Relational Deep Learning Architecture: Treat any enterprise relational database as a graph where tables are nodes and foreign key relationships are edges, then apply graph transformer attention mechanisms across this structure. This eliminates the need to manually join tables or pre-define SQL aggregations before training, letting the model learn which data combinations matter for a given prediction task.
•Foundation Model for Tabular Data (Kumo RFM): A single pre-trained foundation model can connect to any structured database schema and answer predictive queries without task-specific retraining. Users define predictions using a structured "predictive query" language — for example, specifying churn as zero transactions in the next 30 days — and the frozen model fetches relevant subgraphs and returns probability scores on demand.
•Feature Engineering Cost Reduction: Traditional predictive modeling requires approximately two full-time data scientists per production model, making 10 simultaneous models a 20-person commitment. Relational deep learning eliminates manual feature engineering by attending directly over raw database rows, columns, and linked tables, compressing that multi-person effort into a single reusable model infrastructure.
•Model Size and Inference Efficiency: Relational deep learning models operate below one billion parameters, significantly smaller than large language models, enabling faster and cheaper inference. However, they require a specialized graph engine backend that optimizes database representations into graph form and supports subgraph sampling at scale across tens to hundreds of billions of nodes and edges.
•Synthetic Pre-Training Data via Plural Method: A Stanford research paper called Plural demonstrates that synthetic structured tabular data can be generated at scale to pre-train relational foundation models, solving the data scarcity problem that would otherwise limit training. For high-throughput production use cases like real-time fraud scoring at millions of transactions per second, fine-tuning a smaller distilled version of the pre-trained model delivers speed and cost efficiency.

Notable Moment

Leskovec draws a direct parallel to computer vision: just as hand-engineering elephant-detection features became obsolete once neural networks learned directly from pixels, manually engineering database features for churn or fraud models will become equally obsolete as graph transformers learn directly from raw relational data.

Know someone who'd find this useful?

Episode Transcript

Predictive modeling is a core element in modern systems and powers capabilities such as fraud detection, loan approvals, and recommendation systems. These systems typically operate on structured relational data stored in enterprise databases with rows, columns, and interlinked tables. While computer vision and natural language processing have undergone a neural network revolution, the tabular data layer underpinning predictive modeling still largely relies on manual feature engineering and task specific models. Relational deep learning proposes a new approach. It treats databases as graphs and applies transformer style attention mechanisms directly over structured relational data. Researchers are now building foundation models for tabular data that aim to generalize across predictive tasks without painstaking feature engineering. Jura Leskiewicz is a professor of computer science at Stanford University, and he previously served as chief scientist at Pinterest and was an investigator at the Chan Zuckerberg Biohub. Most recently, he co founded the machine learning startup Qumo AI. In this episode, you rejoin Sean Falconer to discuss the limitations of traditional predictive modeling, why structured enterprise data requires its own modality specific neural architectures, how graph transformers generalize attention to relational databases, and more. This episode is hosted by Sean Falconer. Check the show notes for more information on Sean's work and where to find him. Yuri, welcome to the show. Thanks for having me. Great to be here. I'm really excited to get into I think there's a variety of topics we can dive into today. But maybe before we get there, just to kinda grind on the audience a little bit. Like, who are you? What do you do? What's sort of your background? Yeah. I am primarily a professor at the computer science department, AI lab at Stanford. Been there fifteen years. My research focus on AI, especially AI over a structured tabular relational type data. I work a lot with graph data. And in my career, the models we've developed are today used at Facebook, at Meta, at YouTube, and at a number of different places. In my career, I was also a chief scientist at Pinterest for six years, grew Pinterest from 150 employees post IPO and then was basically building large scale AI and machine learning platforms there. What drew you back to academics after having experience at a place like Pinterest? I think Stanford is the most amazing place. It's where the future happens. And what is also amazing about Stanford is that it has this allow us to kind of flow between industry and academia and really understand what are the biggest problems out there that are worth solving. We go to the industry, we come back with the ideas. The students at Stanford are amazing. And I would really say kind of the future happens at Stanford, and that's the most exciting part to me. Yeah. I spent some time at Stanford myself as a student and then was drawn out to industry and never found my found my way back. But I guess, like, now …

Get the full transcript (8,409 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all Software Engineering Daily transcripts →

You just read a 3-minute summary of a 41-minute episode.

Get Software Engineering Daily summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

The Terminal as an Agentic Interface

Aug 6 · 52 min

The TWIML AI Podcast

Relational Foundation Models for Enterprise Data with Jure Leskovec - #768

May 21

AI-Powered Threats to the Software Supply Chain

Aug 4 · 57 min

Beyond Biotech

How Epic Bio is leveraging CRISPR without cutting DNA

Apr 30

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links. As an Amazon Associate, SignalCast earns from qualifying purchases.

Books

Plural
“A Stanford research paper called Plural demonstrates that synthetic structured tabular data can be generated at scale to pre-train relational foundation models, solving the data scarcity problem that would otherwise limit training.”
Bookshop Amazon Audible trial

Products

Kumo RFM
by Kumo AI
“A single pre-trained foundation model can connect to any structured database schema and answer predictive queries without task-specific retraining...the frozen model fetches relevant subgraphs and returns probability scores on demand.”
Amazon