4 papers
Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces
Aditya Desai, Benjamin Meisburger, Zichang Liu +1
Recommendation systems (RS) for items (e.g., movies, books) and ads are widely used to tailor content to users on various internet platforms. Traditionally, recommendation models a…
In defense of parameter sharing for model-compression
Aditya Desai, Anshumali Shrivastava
When considering a model architecture, there are several ways to reduce its memory footprint. Historically, popular approaches included selecting smaller architectures and creating…
The trade-offs of model size in large recommendation models : A 10000 compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)
Aditya Desai, Anshumali Shrivastava
Embedding tables dominate industrial-scale recommendation model sizes, using up to terabytes of memory. A popular and the largest publicly available machine learning MLPerf benchma…
Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing
Aditya Desai, Keren Zhou, Anshumali Shrivastava
Advancements in deep learning are often associated with increasing model sizes. The model size dramatically affects the deployment cost and latency of deep models. For instance, mo…