We'll look into this. The algorithm does not do face detection at all (it actually replaced a previous algorithm which did). We conducted some bias studies before release back in 2017. At the time we found that there was no significant bias between ethnicities (or genders).

Appreciate you looking into this and sharing your work. Checking with the team to approve your Cropping_bias account.

thanks to everyone who raised this. we tested for bias before shipping the model and didn't find evidence of racial or gender bias in our testing, but it’s clear that we’ve got more analysis to do. we'll open source our work so others can review and replicate.

Today is the day! RecSysChallenge #RecSysChallenge2020 #recsys

What Twitter learned from the Recsys 2020 Challenge by Michael Bronstein buff.ly/2FZoSHc

Watched live cricket after so many years. What a test match and series. What a victory for India. Amazing! #INDvAUS

Very insightful and easy digest. Thanks Sameer Singh

We are proud to announce the #RecSys2021 challenge! The data for this year's challenge is provided by @TwitterResearch. This year's goal is two-fold: predict different engagement types, while providing fair recommendations. More details on our website: recsys.acm.org/recsys21/chall…

Responsible ML isn't a team, it's a company-wide imperative. With META as the driver, we're excited to share our new RML initiative. 1/5

What is in common between CNNs, GNNs, LSTMs, Transformers, DeepSets, mesh CNNs? In a new post with @joanbruna Taco Cohen Petar Veličković we show this zoo of neural nets can be seen through the lens of symmetry. #geometricdeeplearning is all you need! tinyurl.com/b53bvwbx

Italy is 1-1 W/L between Wimbledon and UEFA today. What a day!

Our latest Twitter engineering blogpost, coauthored with Michael Bronstein is now available: Graph Neural Networks as Neural Diffusion PDEs blog.twitter.com/engineering/en…

Proud to see Twitter Cortex supporting ML research by donating scholarships to Cambridge Computer Science.

3 #NeurIPS2021 papers: 1.Non-Euclidean diffusion PDEs on graphs, linking GNNs with differential geometry (not public yet) 2.Provably expressive Cellular message passing GNNs 3.Neural compression of graphs Congrats to all the collaborators! Details/blog posts will follow

#ThankYouJack for being such a great leader for Twitter during some of our most difficult times. We will miss you but I'm sure the culture and philosophy you have imbibed will stay with us.

AWESOME👏👏👏 In 2017, a boy asked Roger Federer: “Can you please continue to play for 8-9 years so that I can play you when I go pro?”

To my tennis family and beyond, With Love, Roger

End of an era #RForever

After the big three, we may have finally found the next men’s champion for years to come #Alcaraz