Deep Learning Recommendation Model for Personalization and Recommendation Systems · HackerPapers discussions

Deep Learning Recommendation Model for Personalization and Recommendation Systems — mentioned by ipsum2

Fri, 07 Mar 2025 19:16:23 GMT

> You’ll note that nobody is open sourcing their ad recommender Actually... (2019) https://ai.meta.com/blog/dlrm-an-advanced-open-source-deep-l... Source code: https://github.com/facebookresearch/dlrm Paper: https://arxiv.org/abs/1906.00091 Updated 2023 blog post, but solely for content recommendation, but ads recommendation is ~90% the same: https://engineering.fb.com/2023/08/09/ml-applications/scalin... It's a little out of date, but the internal one is built with the same concepts, just more advanced modeling techniques and data.

Paper and discussion history. A mention is not an endorsement.

Deep Learning Recommendation Model for Personalization and Recommendation Systems — mentioned by benreesman

Tue, 12 Mar 2024 21:42:56 GMT

I think it’s always useful to pay attention to the history on stuff like this and it’s a rare pleasure to be able to give some pointers in the literature along with some color to those interested from first-hand experience. I’d point the interested at the DLRM paper [1]: that was just after I left and I’m sad I missed it. FB got into disagg racks and SDN and stuff fairly early, and we already had half-U dual-socket SKUs with the SSD and (increasingly) even DRAM elsewhere in the rack in 2018, but we were doing huge NNs for recommenders and rankers even for then. I don’t know if this is…

Paper and discussion history. A mention is not an endorsement.

Deep Learning Recommendation Model for Personalization and Recommendation Systems — mentioned by yvdriess

Fri, 06 Mar 2020 13:39:37 GMT

So you agree that the problem is fundamentally sparse? Embeddings are used to make sparse (e.g. categorical) data possible on GPUs, and real-world models are limited by how large they can make the embeddings to fit in GPU memory. Embedding lookups is also a compute bottleneck: An example is facebook DLRM: https://arxiv.org/pdf/1906.00091.pdf

Paper and discussion history. A mention is not an endorsement.

Deep Learning Recommendation Model for Personalization and Recommendation Systems — mentioned by yvdriess

Fri, 06 Mar 2020 13:22:46 GMT

The reverse is true, embeddings are both the performance and memory-footprint bottleneck of modern NN models. Check figure 6. of : https://arxiv.org/pdf/1906.00091.pdf Embeddings are used to lookup sparse features, so you have those pesky data-dependent lookups.

Paper and discussion history. A mention is not an endorsement.