Blog posts about Cortex

Over-squashing is a common plight of Graph Neural Networks occurring when message passing fails to propagate informat...

Graphs are a core asset at Twitter, describing how users interact with each other through Follows, Tweets, Topics, an...

As part of our commitment to responsible machine learning (ML), we’re continuously looking for opportunities to advan...

It’s important that people can easily find and connect with the content and conversations they’re interested in when ...

Introduction Within Cortex Platform (Twitter’s ML Platform group), the Experimentation Tools (ET) team is chartered ...

Differential geometry and algebraic topology are not encountered very frequently in mainstream machine learning. In a...

The Twitter Cortex team has been focused on improving content understanding to extract new topics, promote healthy co...

At Twitter, our core data assets are huge graphs that describe how users interact with each other through Follows, Tw...

In October 2020, we heard feedback from people on Twitter that our image cropping algorithm didn’t serve all people e...

Microservice-based companies distribute accountability for data privacy throughout an organization. Tracing and accou...

In the previous post in our series on distributed training of sparse ML models, we described the techniques we use to...

In Part 1, on network bottleneck issues, we discussed the sparse models that are common at Twitter and the difficulti...

At Twitter, we use machine learning (ML) models in many applications, from ad selection, to abuse detection, to conte...

Deep learning on graphs — also known as Geometric deep learning (GDL)¹, Graph representation learning (GRL), or relat...

For more than a year now since we enhanced our timeline to show the best Tweets for you first, we have worked to impr...

We recently released Autograd for Torch, which greatly simplified our workflow when experimenting with complex deep l...

e recently established the Twitter Cortex team with a simple mission: to build a representation layer for Twitter in ...