paper-with-me

Papers

Exploring Low-Cost Transformer Model Compression for Large-Scale Commercial Reply Suggestions

2021-11-27 · Vaishnavi Shrivastava, Radhika Gaonkar, Shashank Gupta, Abhishek Jha

Fine-tuning pre-trained language models improves the quality of commercial reply suggestion systems, but at the cost of unsustainable training times. Popular training time reduction approaches are resource intensive, thus we explore low-cost model compression techniques like Layer Dropping and Layer Freezing. We demonstrate the efficacy of these techniques in large-data scenarios, enabling the training time reduction for a commercial email reply suggestion system by 42%, without affecting the model relevance or user engagement. We further study the robustness of these techniques to pre-trained model and dataset size ablation, and share several insights and recommendations for commercial applications.

📄 PDF Abstract BibTeX arXiv:2111.13999

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Similar Papers 제목 키워드 기반

Exploring Extreme Parameter Compression for Pre-trained Language Models

2022-05-20 · ICLR 2022 4 · Yuxin Ren, Benyou Wang, Lifeng Shang, Xin Jiang 외

Recent work explored the potential of large-scale Transformer-based pre-trained models, especially Pre-trained Language Models (PLMs) in natural language processing. This raises many concerns from various perspectives, e…

Knowledge DistillationTensor Decomposition

Exploring Effective Mask Sampling Modeling for Neural Image Compression

2023-06-09 · Lin Liu, Mingming Zhao, Shanxin Yuan, Wenlong Lyu 외

Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to eliminate spatial redundancy, but rarely…

Image CompressionSelf-Supervised Learning

Amber-Image: Efficient Compression of Large-Scale Diffusion Transformers

2026-02-19 · Chaojie Yang, Tian Li, Yue Zhang, Jun Gao arxiv

Diffusion Transformer (DiT) architectures have significantly advanced Text-to-Image (T2I) generation but suffer from prohibitive computational costs and deployment barriers. To address these challenges, we propose an eff…

A Survey on Transformer Compression

2024-02-05 · Yehui Tang, Yunhe Wang, Jianyuan Guo, Zhijun Tu 외

Transformer plays a vital role in the realms of natural language processing (NLP) and computer vision (CV), specially for constructing large language models (LLM) and large vision models (LVM). Model compression methods …

Knowledge DistillationMambaModel CompressionQuantization+1

UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence

2026-05-09 · Hongwei Zhang, Qiqiang Zhong, Jiangxia Cao, Yiyang Lv 외 arxiv

Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-specific search or item-agnostic compression, we propose UxSID, a framew…