What is PyTorch | Building Recommender Systems with PyTorch | Joseph Spisak and Geeta Chauhan

In this tutorial series we show how to build deep learning recommendation systems and resolve the associated interpretability, integrity and privacy challenges. We start with an overview of the PyTorch framework, features that it offers and a brief review of the evolution of recommendation models. We delineate their typical components and build a proxy deep learning recommendation model (DLRM) in PyTorch. Then, we discuss how to interpret recommendation system results as well as how to address the corresponding integrity and quality challenges. The material for this section covers:

𝟭. 𝗪𝗵𝗮𝘁 𝗶𝘀 𝗣𝘆𝗧𝗼𝗿𝗰𝗵? 𝗝𝗼𝗲 𝗦𝗽𝗶𝘀𝗮𝗸/𝗚𝗲𝗲𝘁𝗮 𝗖𝗵𝗮𝘂𝗵𝗮𝗻

2. Recommender Systems using DLRM – Maxim Naumov/Dheevatsa Mudigere
3. Using Captum for Interpretability for recommender systems – Narine Kokhlikyan
4. Solving integrity / QC challenges for recommender systems – Amanpreet Singh

Important references that will be covered in the tutorial:
https://pytorch.org/
https://github.com/facebookresearch/dlrm
https://captum.ai/
https://ai.facebook.com/blog/dlrm-an-advanced-open-source-deep-learning-recommendation-model/
Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems (https://arxiv.org/abs/1909.02107)
Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems (https://arxiv.org/abs/1909.11810)
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications (https://arxiv.org/abs/1811.09886)
Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems (https://arxiv.org/abs/2003.09518)
https://paperswithcode.com/paper/the-architectural-implications-of-facebooks

Source of this PyTorch AI Video

AI video(s) you might be interested in …