Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems
원문 초록
Huge embedding tables in modern deep learning recommender models (DLRM) require prohibitively large memory during training and inference. This paper proposes FIITED, a system to automatically reduce the memory footprint via FIne-grained In-Training Embedding Dimension pruning. By leveraging the key insight that embedding vectors are not equally important, FIITED adaptively adjusts the dimension of each individual embedding vector during model training, assigning larger dimensions to more important embeddings while adapting to dynamic changes in data. We prioritize embedding dimensions with higher frequencies and gradients as more important. To enable efficient pruning of embeddings and their dimensions during model training, we propose an embedding storage system based on virtually-hashed physically-indexed hash tables. Experiments on two industry models and months of realistic datasets show that FIITED can reduce DLRM embedding size by more than 65% while preserving model quality, outperforming state-of-the-art in-training embedding pruning methods. On public datasets, FIITED can reduce the size of embedding tables by 2.1x to 800x with negligible accuracy drop, while improving model throughput.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
DLF: Enhancing Explicit-Implicit Interaction via Dynamic Low-Order-Aware Fusion for CTR Prediction
Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction
1$^{st}$ Place Solution of WWW 2025 EReL@MIR Workshop Multimodal CTR Prediction Challenge
Feature Staleness Aware Incremental Learning for CTR Prediction
Feature Fusion Revisited: Multimodal CTR Prediction for MMCTR Challenge
토론
이 논문과 연결된 포럼 글이 아직 없습니다.