4 citations · 4 across the 2 of their papers we have counts for
2 papers
cs.IR2025
DV365: Extremely Long User History Modeling at Instagram
Wenhan Lyu, Devashish Tyagi, Yihang Yang +9
Long user history is highly valuable signal for recommendation systems, but effectively incorporating it often comes with high cost in terms of data center power consumption and GP…
cs.LG2022★ 4 cited
RecD: Deduplication for End-to-End Deep Learning Recommendation Model Training Infrastructure
Mark Zhao, Dhruv Choudhary, Devashish Tyagi +9
We present RecD (Recommendation Deduplication), a suite of end-to-end infrastructure optimizations across the Deep Learning Recommendation Model (DLRM) training pipeline. RecD addr…