large-scale AI | BestHub

DataFunTalk

Jan 7, 2024 · Artificial Intelligence

Baidu's Recommendation Ranking: Background, Feature Design, Algorithms, Architecture, and Future Directions

This article presents Baidu's comprehensive approach to feed recommendation ranking, covering business and data background, feature engineering principles, core algorithmic strategies, system architecture design, and upcoming plans to integrate large language models for more intelligent and fair recommendations.

BaiduFeature EngineeringRecommendation systems

0 likes · 19 min read

Baidu's Recommendation Ranking: Background, Feature Design, Algorithms, Architecture, and Future Directions

Kuaishou Tech

Oct 26, 2023 · Artificial Intelligence

SHARK: Efficient Embedding Compression for Large-Scale Recommendation Models

The paper introduces SHARK, a two‑component framework that uses a fast Taylor‑expanded permutation method to prune embedding tables and a frequency‑aware quantization scheme to apply mixed‑precision to embeddings, achieving up to 70% memory reduction and 30% QPS improvement in industrial short‑video and e‑commerce recommendation systems.

efficiencyembedding compressionlarge-scale AI

0 likes · 8 min read

SHARK: Efficient Embedding Compression for Large-Scale Recommendation Models

AntTech

Feb 24, 2023 · Artificial Intelligence

Large-Scale Complex Heterogeneous Graph Data Intelligent Analysis Technology Wins 2022 CIEE Science and Technology Award

The 2022 China Institute of Electronics (CIEE) Science and Technology Award recognized a collaborative project between Beijing University of Posts and Telecommunications and Ant Group for pioneering large-scale heterogeneous graph neural network models, a trillion‑scale dynamic graph learning system, and extensive industry applications, earning top honors, patents, papers, and standards.

Big DataGraph Neural NetworksTechnology Award

0 likes · 4 min read

Large-Scale Complex Heterogeneous Graph Data Intelligent Analysis Technology Wins 2022 CIEE Science and Technology Award

Tencent Tech

Aug 26, 2020 · Artificial Intelligence

How Tencent Engineers Shattered the 128‑GPU ImageNet Training Record in 2m31s

Tencent engineers broke the world record for training ImageNet with 128 V100 GPUs in just 2 minutes 31 seconds, detailing a suite of optimizations—including a new Light distributed training framework, single‑machine speed boosts, multi‑machine communication enhancements, and advanced batch convergence techniques—that together dramatically cut training time while maintaining high accuracy.

GPUImageNetTencent Cloud

0 likes · 9 min read

How Tencent Engineers Shattered the 128‑GPU ImageNet Training Record in 2m31s