Merlin NVTabular：基于 GPU 加速的推荐系统特征工程最佳实践.pdf

《Merlin NVTabular：基于 GPU 加速的推荐系统特征工程最佳实践.pdf》由会员分享，可在线阅读，更多相关《Merlin NVTabular：基于 GPU 加速的推荐系统特征工程最佳实践.pdf（29页珍藏版）》请在三个皮匠报告上搜索。

1、NVIDIAMerlinNVTabular:基于GPU加速的推荐系统特征工程最佳实践黄孟迪，NVIDIA深度学习工程师#page#RELATED SESSIONS IN GTC CHINALearning More About NVIDIA MerlinMerlin：GPU加速的推荐系统框架CNS20590王泽衰，英伟达亚太AI开发者技术经理，NVIDIAMerlinHugeCTR：深入研究性能优化CNS20516MinseokLee，GPU计算专家，NVIDIAMerlinNVTabular：基于GPU加速的推荐系统特征工程最佳实践CNS20624黄孟迪，深度学习工程师，NVIDIAGPU加

2、速的数据处理在推荐系统中的应用CNS20813魏英灿，GPU计算专家，NVIDIA将HugeCTREmbedding集成于TensorFlowCNS20377董建兵，GPU计算专家，NVIDIA使用GPUembeddingcache加速CTR推理过程CNS20626郁凡，GPU计算专家，NVIDIA#page#Merlin OverviewNVTabular- Merlin ETLTutorials- Best Practices For RecSysAgendaFeature EngineeringGoal 1:lmproving Model AccuracyGoal 2: Quick ex

3、perimentation with GPU AccelerationGoal 3: Scale to Production Systems With NVTabular#page#NVIDIAMerlin Overrview#page#Industrial Recommendation ChallengesTrainingFeatureEmbeddingDataloadingDeploymentHigh AccuracyExplorationTablesTabular data scalesLarge embeddingHigh throughput toMultiple iteration

4、s canLonger iteration cyclestables requirerank more items ispoorly using thereduce the ability toconsume a lot of timesignificantmemorydifficult whilecommon deep learningtofindthemostreach highermethod of item byand lookups can havemaintaining lowaccurate feature setaccuracies as quicklylatencyiteme

5、xtrraneous operations#page#Merlin Framework BenefitsNVTabularHugeCTRTritonFeatureDeploymentDataloadingScaling TrainingHigh AccuracyEngineeringHighthroughput，low-Fast iteration time，Acceleratetabular dataOptimal lookupsReach higher accuracylatency productionloading into trainingimplementation.faster.

6、deployment.Prepare massiveframeworks.datasetsin minutesEasy to use data andShorten exploration andInference time dataallowing for moreAsynchronous batchmodel parallel trainingtraining cycles to reachtransforms and multiexploration and betterdataloading meanstheallow you to scale to TBhigher accuraci