Dynamic Embedding

iQIYI Technical Product Team

Mar 1, 2024 · Artificial Intelligence

Advertising Data Characteristics and Sparse Large‑Model Practices at iQIYI

iQIYI’s ad ranking system replaces static, hash‑based embeddings with TFRA dynamic embeddings to efficiently handle massive sparse ID features, eliminates collisions and I/O bottlenecks, isolates memory during hot model swaps, enabling billion‑parameter models that boost revenue by 4.3 % while planning adaptive embedding sizes for future improvements.

AI recommendationDynamic EmbeddingLarge-Scale Models

0 likes · 10 min read

Advertising Data Characteristics and Sparse Large‑Model Practices at iQIYI

DataFunTalk

Apr 3, 2023 · Artificial Intelligence

Large‑Scale Recommendation System Training with TorchRec and Dynamic Embedding

This article explains how Tencent’s AI team leverages the PyTorch‑based TorchRec library and a custom dynamic embedding solution to train billion‑scale recommendation models efficiently, detailing the benefits of TorchRec, GPU embedding, optimized kernels, embedding partition strategies, experimental results, and practical deployment guidance.

Dynamic EmbeddingGPU EmbeddingLarge-Scale Training

0 likes · 15 min read

Large‑Scale Recommendation System Training with TorchRec and Dynamic Embedding