paper-with-me

Papers

Differentiable Product Quantization for Learning Compact Embedding Layers

2020-01-01 · ICML 2020 1 · Ting Chen, Lala Li, Yizhou Sun

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. Despite their effectiveness, the number of parameters in an embedding layer increases linearly with the number of symbols and poses a critical challenge on memory and storage constraints. In this work, we propose a generic and end-to-end learnable compression framework termed differentiable product quantization (DPQ). We present two instantiations of DPQ that leverage different approximation techniques to enable differentiability in end-to-end learning. Our method can readily serve as a drop-in alternative for any existing embedding layer. Empirically, DPQ offers significant compression ratios (14-238x) at negligible or no performance cost on 10 datasets across three different language tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Learning Compact Embedding Layers via Differentiable Product Quantization

2019-09-25 · Ting Chen, Lala Li, Yizhou Sun

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. Despite their effectiveness, the number of parameters in an embedding layer increases lin…

Quantization

Differentiable Product Quantization for End-to-End Embedding Compression

2019-08-26 · Ting Chen, Lala Li, Yizhou Sun

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. Despite their effectiveness, the number of parameters in an embedding layer increases lin…

Quantization

Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution

2021-06-04 · Zhang Zhaoyang, Shao Wenqi, Gu Jinwei, Wang Xiaogang 외

Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts …

Quantization

Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems

2020-02-20 · Wang-Cheng Kang, Derek Zhiyuan Cheng, Ting Chen, Xinyang Yi 외

Recommender system models often represent various sparse features like users, items, and categorical features via embeddings. A standard approach is to map each unique feature value to an embedding vector. The size of th…

QuantizationRecommendation Systems

Matching-oriented Embedding Quantization For Ad-hoc Retrieval

2021-11-01 · EMNLP 2021 11 · Shitao Xiao, Zheng Liu, Yingxia Shao, Defu Lian 외

Product quantization (PQ) is a widely used technique for ad-hoc retrieval. Recent studies propose supervised PQ, where the embedding and quantization models can be jointly trained with supervised learning. However, there…

QuantizationRetrieval