awesome-twitter-algo/masknet.md at main · igorbrigadir/awesome-twitter-algo

The release of the Twitter algorithm, annotated for recsys - awesome-twitter-algo/masknet.md at main · igorbrigadir/awesome-twitter-algo

Twitter Model Architecture Summary Summary Because of the high number of categorical features and important interaction effects, Ads/RecSys models often use models which specifically incorporate cross features (the interaction of two features). We review a couple different approaches to this problem and explain how MaskNet, the model used by the Twitter heavy ranker, works. Background Let's suppose you have a friend @username on Twitter and you only retweet their tweets about cats. You follow them, but you don't want to see their tweets about dogs (on Twitter these days people only like cats).

related reading

• GitHub - igorbrigadir/awesome-twitter-algo: The release of the Twitter algorithm, annotated for recsys · GitHubgithub.com
• Toy Models of Superpositiontransformer-circuits.pub
• the-algorithm/src/scala/com/twitter/simclusters_v2/README.md at main · twitter/the-algorithmgithub.com
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• Analysis of 2025 X Algorithmgist.github.com
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• Wide & Deep Learning for Recommender Systems | by Atul Anand | Analytics Vidhya | Mediummedium.com
• DeltaNet Explained (Part I) | Songlin Yangsustcsonglin.github.io
• Tensor-Transformer Variants are Surprisingly Performant — LessWronglesswrong.com
• Understanding Convolutions on Graphsdistill.pub
• Insights on Crosscoder Model Diffingtransformer-circuits.pub
• The Annotated Transformernlp.seas.harvard.edu