mlsanityData to 14 Oct 2026

TwERC: High Performance Ensembled Candidate Generation for Ads Recommendation at Twitter

arXiv 2302.13915 ↗First posted 27 Feb 2023cs.IR cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Recommendation systems are a core feature of social media companies with their uses including recommending organic and promoted contents. Many modern recommendation systems are split into multiple stages - candidate generation and heavy ranking - to balance computational cost against recommendation quality. We focus on the candidate generation phase of a large-scale ads recommendation problem in this paper, and present a machine learning first heterogeneous re-architecture of this stage which we term TwERC. We show that a system that combines a real-time light ranker with sourcing strategies capable of capturing additional information provides validated gains. We present two strategies. The first strategy uses a notion of similarity in the interaction graph, while the second strategy caches previous scores from the ranking stage. The graph based strategy achieves a 4.08% revenue gain and the rankscore based strategy achieves a 1.38% gain. These two strategies have biases that complement both the light ranker and one another. Finally, we describe a set of metrics that we believe are valuable as a means of understanding the complex product trade offs inherent in industrial candidate generation systems.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 73 references that are in the map. First posted on arXiv 27 Feb 2023.

Builds on

29 of 73 references.

References · 29

  1. 2017Inductive Representation Learning on Large Graphscited by 6,320
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  4. 2017Billion-scale similarity search with GPUscited by 2,497
  5. 2017Neural Collaborative Filteringcited by 1,111
  6. 2016Wide & Deep Learning for Recommender Systemscited by 747
  7. 2019Graph Neural Networks for Social Recommendationcited by 714
  8. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  9. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
  10. 2017Deep & Cross Network for Ad Click Predictionscited by 393
  11. 2019Deep Learning Recommendation Model for Personalization and Recommendation Systemscited by 327
  12. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 327
17 more
  1. 2020SIGN: Scalable Inception Graph Neural Networkscited by 284
  2. 2016Unbiased Learning-to-Rank with Biased Feedbackcited by 157
  3. 2019PyTorch-BigGraph: A Large-scale Graph Embedding Systemcited by 119
  4. 2021A Review on Graph Neural Network Methods in Financial Applicationscited by 78
  5. 2016Item2Vec: Neural Item Embedding for Collaborative Filteringcited by 72
  6. 2020DGL-KE: Training Knowledge Graph Embeddings at Scalecited by 67
  7. 2021On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Featurescited by 63
  8. 2020Graph Neural Networks with Continual Learning for Fake News Detection from Social Mediacited by 43
  9. 2019GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embeddingcited by 40
  10. 2022On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Modelscited by 34
  11. 2020A Comprehensive Survey on Word Representation Models: From Classical to State-Of-The-Art Word Representation Language Modelscited by 30
  12. 2019Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysiscited by 27
  13. 2022TwHIN: Embedding the Twitter Heterogeneous Information Network for Personalized Recommendationcited by 25
  14. 2022Neural Re-ranking in Multi-stage Recommender Systems: A Reviewcited by 20
  15. 2019Candidate Generation with Binary Codes for Large-Scale Top-N Recommendationcited by 19
  16. 2022IntTower: the Next Generation of Two-Tower Model for Pre-Ranking Systemcited by 18
  17. 2021Recommender systems based on graph embedding techniques: A comprehensive reviewcited by 8

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025RADAR: Recall Augmentation through Deferred Asynchronous Retrievalcited by 0
  2. 2025MaRCA: Multi-Agent Reinforcement Learning for Dynamic Computation Allocation in Large-Scale Recommender Systemscited by 0