From RecSysWiki
Jump to navigation Jump to search

Meta is the parent company of Facebook, Instagram, and WhatsApp.

Blog posts

  1. The new AI-powered feature designed to improve Feed for everyone, 2022-10-05
  2. When do recommender systems amplify user preferences? A theoretical framework and mitigation strategies, 2021-08
  3. Efficient tuning of online systems using Bayesian optimization
  4. On the value of diversified recommendations, 2020-12-17
  5. How Instagram suggests new content, 2020-12-10
  6. Five things I learned about working on content quality at Instagram, 2020-01-25
  7. 🕴 Instagram’s Explore Recommender System, 2019-11-26 HackerNews discussion
    • 3-part funnel (2 layers of candidate generation)
    • domain-specific language (We have separation between model and filter config).
    • account embeddings
    • embedding-based
    • “See fewer posts like this” – explicit feedback
  8. Offline Policy Evaluation: Run fewer, better A/B tests
  9. DLRM: An advanced, open source deep learning recommendation model, 2019-07-02


  1. 🔩🏃 AutoShard: Automated Embedding Table Sharding for Recommender Systems, KDD 2022
  2., JMLR, 2021
  3. Preference Amplification in Recommender Systems, KDD 2021
  4. 🔍 Embedding-based Retrieval in Facebook Search, KDD 2020
  5. Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems, KDD 2020
  6. 👗 Modeling Fashion Influence from Photos, IEEE Transactions on Multimedia, 2020
  7. 🧠 Deep Learning Recommendation Model for Personalization and Recommendation Systems, 2019 (DLRM)
  8. 💵 Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising
  9. Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems
  10. 💵 Practical lessons from predicting clicks on ads at facebook, workshop 2014
  11. Supervised Random Walks: Predicting and Recommending Links in Social Networks, WSDM 2011


  1. DLRM recommender: click probability model
  2. Prophet: forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects.
  3. Facebook AI Performance Evaluation Platform: framework and backend agnostic benchmarking platform to compare machine learning inferencing runtime metrics on a set of models and on variety of backends.
  4. 📑 StarSpace: Learning embeddings for classification, retrieval and ranking.
  5. ReAgent/Horizon: end-to-end platform designed to solve industry applied RL problems where datasets are large (millions to billions of observations), the feedback loop is slow (vs. a simulator), and experiments must be done with care because they don’t run in a simulator. Tutorial contains e-commerce/recommendation example. paper
  6. faiss: library for efficient similarity search and clustering of dense vectors.
  7. pysparnn: approximate nearest neighbor search for sparse data in Python.
  8. Ax: adaptive experimentation platform,

External links