Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.15438 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915031483940864 |
|---|---|
| author | Chen, Jiayi Wu, Chen Zhang, Shaoqun Li, Nan Zhang, Liangjie Zhang, Qi |
| author_facet | Chen, Jiayi Wu, Chen Zhang, Shaoqun Li, Nan Zhang, Liangjie Zhang, Qi |
| contents | Embedding models have become essential tools in both natural language processing and computer vision, enabling efficient semantic search, recommendation, clustering, and more. However, the high memory and computational demands of full-precision embeddings pose challenges for deployment in resource-constrained environments, such as real-time recommendation systems. In this work, we propose a novel finetuning framework to ternary-weight embedding models, which reduces memory and computational overhead while maintaining high performance. To apply ternarization to pre-trained embedding models, we introduce self-taught knowledge distillation to finalize the ternary-weights of the linear layers. With extensive experiments on public text and vision datasets, we demonstrated that without sacrificing effectiveness, the ternarized model consumes low memory usage and has low latency in the inference stage with great efficiency. In practical implementations, embedding models are typically integrated with Approximate Nearest Neighbor (ANN) search. Our experiments combining ternary embedding with ANN search yielded impressive improvement in both accuracy and computational efficiency. The repository is available at here. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15438 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Ternary Weight Embedding Model: Bridging Scalability and Performance Chen, Jiayi Wu, Chen Zhang, Shaoqun Li, Nan Zhang, Liangjie Zhang, Qi Computation and Language Embedding models have become essential tools in both natural language processing and computer vision, enabling efficient semantic search, recommendation, clustering, and more. However, the high memory and computational demands of full-precision embeddings pose challenges for deployment in resource-constrained environments, such as real-time recommendation systems. In this work, we propose a novel finetuning framework to ternary-weight embedding models, which reduces memory and computational overhead while maintaining high performance. To apply ternarization to pre-trained embedding models, we introduce self-taught knowledge distillation to finalize the ternary-weights of the linear layers. With extensive experiments on public text and vision datasets, we demonstrated that without sacrificing effectiveness, the ternarized model consumes low memory usage and has low latency in the inference stage with great efficiency. In practical implementations, embedding models are typically integrated with Approximate Nearest Neighbor (ANN) search. Our experiments combining ternary embedding with ANN search yielded impressive improvement in both accuracy and computational efficiency. The repository is available at here. |
| title | Efficient Ternary Weight Embedding Model: Bridging Scalability and Performance |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.15438 |