Structural Pruning of Pre-trained Language Models via Neural Architecture Search

• URL: http://arxiv.org/abs/2405.02267v2
• Date: Sun, 25 Aug 2024 14:41:32 GMT
• Title: Structural Pruning of Pre-trained Language Models via Neural Architecture Search
• Authors: Aaron Klein, Jacek Golebiowski, Xingchen Ma, Valerio Perrone, Cedric Archambeau,
• Abstract summary: Pre-trained language models (PLM) mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. This paper explores neural architecture search (NAS) for structural pruning to find sub-parts of the fine-tuned network that optimally trade-off efficiency.
• Score: 7.833790713816726
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pre-trained language models (PLM), for example BERT or RoBERTa, mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. However, their large size poses challenges in deploying them for inference in real-world applications, due to significant GPU memory requirements and high inference latency. This paper explores neural architecture search (NAS) for structural pruning to find sub-parts of the fine-tuned network that optimally trade-off efficiency, for example in terms of model size or latency, and generalization performance. We also show how we can utilize more recently developed two-stage weight-sharing NAS approaches in this setting to accelerate the search process. Unlike traditional pruning methods with fixed thresholds, we propose to adopt a multi-objective approach that identifies the Pareto optimal set of sub-networks, allowing for a more flexible and automated compression process.

Related papers

• POMONAG: Pareto-Optimal Many-Objective Neural Architecture Generator [4.09225917049674]
  Transferable NAS has emerged, generalizing the search process from dataset-dependent to task-dependent. This paper introduces POMONAG, extending DiffusionNAG via a many-optimal diffusion process. Results were validated on two search spaces -- NAS201 and MobileNetV3 -- and evaluated across 15 image classification datasets.
  arXiv  Detail & Related papers  (2024-09-30T16:05:29Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)
• PDSketch: Integrated Planning Domain Programming and Learning [86.07442931141637]
  We present a new domain definition language, named PDSketch. It allows users to flexibly define high-level structures in the transition models. Details of the transition model will be filled in by trainable neural networks.
  arXiv  Detail & Related papers  (2023-03-09T18:54:12Z)
• Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation [11.866947846619064]
  neural architecture search (NAS) has emerged as a promising avenue toward automating the design of architectures. We propose a surrogate-assisted multi-objective method to address the challenges of applying NAS to semantic segmentation. Our method can identify architectures significantly outperforming existing state-of-the-art architectures designed both manually by human experts and automatically by other NAS methods.
  arXiv  Detail & Related papers  (2022-08-14T10:18:51Z)
• Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization [50.50023451369742]
  Pruning-as-Search (PaS) is an end-to-end channel pruning method to search out desired sub-network automatically and efficiently. Our proposed architecture outperforms prior arts by around $1.0%$ top-1 accuracy on ImageNet-1000 classification task.
  arXiv  Detail & Related papers  (2022-06-02T17:58:54Z)
• Efficient Nearest Neighbor Language Models [114.40866461741795]
  Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore. We show how to achieve up to a 6x speed-up in inference speed while retaining comparable performance.
  arXiv  Detail & Related papers  (2021-09-09T12:32:28Z)
• Elastic Architecture Search for Diverse Tasks with Different Resources [87.23061200971912]
  We study a new challenging problem of efficient deployment for diverse tasks with different resources, where the resource constraint and task of interest corresponding to a group of classes are dynamically specified at testing time. Previous NAS approaches seek to design architectures for all classes simultaneously, which may not be optimal for some individual tasks. We present a novel and general framework, called Elastic Architecture Search (EAS), permitting instant specializations at runtime for diverse tasks with various resource constraints.
  arXiv  Detail & Related papers  (2021-08-03T00:54:27Z)
• AutoBERT-Zero: Evolving BERT Backbone from Scratch [94.89102524181986]
  We propose an Operation-Priority Neural Architecture Search (OP-NAS) algorithm to automatically search for promising hybrid backbone architectures. We optimize both the search algorithm and evaluation of candidate models to boost the efficiency of our proposed OP-NAS. Experiments show that the searched architecture (named AutoBERT-Zero) significantly outperforms BERT and its variants of different model capacities in various downstream tasks.
  arXiv  Detail & Related papers  (2021-07-15T16:46:01Z)
• AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptation [4.793219747021116]
  We perform neural architecture search (NAS) to provide architecture-level perspective and analysis for domain adaptation. We propose bridging this gap by using maximum mean discrepancy and regional weighted entropy to estimate the accuracy metric.
  arXiv  Detail & Related papers  (2021-06-24T17:59:02Z)
• Generalized Latency Performance Estimation for Once-For-All Neural Architecture Search [0.0]
  We introduce two generalizability strategies which include fine-tuning using a base model trained on a specific hardware and NAS search space. We provide a family of latency prediction models that achieve over 50% lower RMSE loss as compared to ProxylessNAS.
  arXiv  Detail & Related papers  (2021-01-04T00:48:09Z)
• Smooth Variational Graph Embeddings for Efficient Neural Architecture Search [41.62970837629573]
  We propose a two-sided variational graph autoencoder, which allows to smoothly encode and accurately reconstruct neural architectures from various search spaces. We evaluate the proposed approach on neural architectures defined by the ENAS approach, the NAS-Bench-101 and the NAS-Bench-201 search spaces.
  arXiv  Detail & Related papers  (2020-10-09T17:05:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.