HuffmanEmbed: Using Huffman Coding for Embedding Table Compression in Deep Learning Recommendation Models
Open Access
- 19 July 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3848-3853
Abstract
No abstract availableThis publication has 17 references indexed in Scilit:
- CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation ModelsProceedings of the ACM on Management of Data, 2024
- An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks2022
- Binary Code based Hash Embedding for Web-scale Applications2021
- cDLRM: Look Ahead Caching for Scalable Training of Recommendation Models2021
- Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems2021
- The Architectural Implications of Facebook's DNN-Based Personalized Recommendation2020
- Deep & Cross Network for Ad Click Predictions2017
- Wide & Deep Learning for Recommender Systems2016
- Feature hashing for large scale multitask learning2009
- A Method for the Construction of Minimum-Redundancy CodesProceedings of the IRE, 1952