mlsanityData to 14 Oct 2026

A Bag of Tricks for Scaling CPU-based Deep FFMs to more than 300m Predictions per Second

arXiv 2407.10115 ↗First posted 14 Jul 2024cs.LG cs.AI cs.IRcited by 1

Not on the map. Why?

Abstract (arXiv)

Field-aware Factorization Machines (FFMs) have emerged as a powerful model for click-through rate prediction, particularly excelling in capturing complex feature interactions. In this work, we present an in-depth analysis of our in-house, Rust-based Deep FFM implementation, and detail its deployment on a CPU-only, multi-data-center scale. We overview key optimizations devised for both training and inference, demonstrated by previously unpublished benchmark results in efficient model search and online training. Further, we detail an in-house weight quantization that resulted in more than an order of magnitude reduction in bandwidth footprint related to weight transfers across data-centres. We disclose the engine and associated techniques under an open-source license to contribute to the broader machine learning community. This paper showcases one of the first successful CPU-only deployments of Deep FFMs at such scale, marking a significant stride in practical, low-footprint click-through rate prediction methodologies.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 10 of its 19 references that are in the map. First posted on arXiv 14 Jul 2024.

Builds on

10 of 19 references.

References · 10

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  3. 2016Wide & Deep Learning for Recommender Systemscited by 747
  4. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 676
  5. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 327
  6. 2018AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networkscited by 320
  7. 2023Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendationcited by 114
  8. 2018A Contextual Bandit Bake-offcited by 64
  9. 2021Towards Efficient Post-training Quantization of Pre-trained Language Modelscited by 39
  10. 2017Field-aware Factorization Machines in a Real-world Online Advertising Systemcited by 21

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction
  2. 2025From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction
  3. 2023MAP: A Model-agnostic Pretraining Framework for Click-through Rate Prediction
  4. 2026AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization
  5. 2024Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs
  6. 2026Native LLM and MLLM Inference at Scale on Apple Silicon
  7. 2026FLASH-MAXSIM: IO-Aware Fused Kernels for Late-Interaction Retrieval
  8. 2026Density Field State Space Models: 1-Bit Distillation, Efficient Inference, and Knowledge Organization in Mamba-2