paper-with-me

홈 › Papers

Structured Pruning for Multi-Task Deep Neural Networks

2023-04-13 · Siddhant Garg, Lijun Zhang, Hui Guan

Although multi-task deep neural network (DNN) models have computation and storage benefits over individual single-task DNN models, they can be further optimized via model compression. Numerous structured pruning methods are already developed that can readily achieve speedups in single-task models, but the pruning of multi-task networks has not yet been extensively studied. In this work, we investigate the effectiveness of structured pruning on multi-task models. We use an existing single-task filter pruning criterion and also introduce an MTL-based filter pruning criterion for estimating the filter importance scores. We prune the model using an iterative pruning strategy with both pruning methods. We show that, with careful hyper-parameter tuning, architectures obtained from different pruning methods do not have significant differences in their performances across tasks when the number of parameters is similar. We also show that iterative structure pruning may not be the best way to achieve a well-performing pruned model because, at extreme pruning levels, there is a high drop in performance across all tasks. But when the same models are randomly initialized and re-trained, they show better results.

📄 PDF Abstract BibTeX arXiv:2304.06840

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Structured Pruning Adapters

2022-11-17 · Lukas Hedegaard, Aman Alok, Juby Jose, Alexandros Iosifidis

Adapters are a parameter-efficient alternative to fine-tuning, which augment a frozen base network to learn new tasks. Yet, the inference of the adapted model is often slower than the corresponding fine-tuned model. To i…

Single Particle Analysis

Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency

2022-04-06 · ACL 2022 5 · Yanyang Li, Fuli Luo, Runxin Xu, Songfang Huang 외

Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning o…

STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning

2024-09-10 · Jaeseong Lee, Seung-won Hwang, Aurick Qiao, Daniel F Campos 외

Mixture-of-experts (MoEs) have been adopted for reducing inference costs by sparsely activating experts in Large language models (LLMs). Despite this reduction, the massive number of experts in MoEs still makes them expe…

GSM8KMixture-of-Experts

Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration

2026-01-06 · Guangxin Wu, Hao Zhang, Zhang Zhibin, Jiafeng Guo 외 arxiv

Large Language Models (LLMs) have achieved remarkable success across a wide spectrum of natural language processing tasks. However, their ever-growing scale introduces significant barriers to real-world deployment, inclu…

PDP: Parameter-free Differentiable Pruning is All You Need

2023-05-18 · NeurIPS 2023 11

DNN pruning is a popular way to reduce the size of a model, improve the inference latency, and minimize the power consumption on DNN accelerators. However, existing approaches might be too complex, expensive or ineffecti…

AllNatural Language Inference