Large language models (LLMs) targeting different deployment scales and sizes are currently produced by training each variant from scratch; this is extremely compute-intensive. In this paper, we investigate if pruning an existing LLM and then re-training it with a fraction (<3%) of the original training data can be a suitable alternative to repeated, full retraining. To this end, we develop a set of practical and effective compression best practices for LLMs that combine depth, width, attention and MLP pruning with knowledge distillation-based retraining; we arrive at these best practices through a detailed empirical exploration of pruning strategies for each axis, methods to combine axes, distillation strategies, and search techniques for arriving at optimal compressed architectures. We use this guide to compress the Nemotron-4 family of LLMs by a factor of 2-4x, and compare their performance to similarly-sized models on a variety of language modeling tasks. Deriving 8B and 4B models from an already pretrained 15B model using our approach requires up to 40x fewer training tokens per model compared to training from scratch; this results in compute cost savings of 1.8x for training the full model family (15B, 8B, and 4B). Minitron models exhibit up to a 16% improvement in MMLU scores compared to training from scratch, perform comparably to other community models such as Mistral 7B, Gemma 7B and Llama-3 8B, and outperform state-of-the-art compression techniques from the literature. We have open-sourced Minitron model weights on Huggingface, with corresponding supplementary material including example code available on GitHub.
University of Liverpool（利物浦大学）；Huawei Ireland Research Center（华为爱尔兰研究中心）
Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational similarity between the pruned and unpruned versions of the same network is maximized. Unlike previous approaches that treat distillation and pruning separately, we use distillation to inform the pruning criteria, without requiring a separate student network as in knowledge distillation. We show that the proposed {\em cross-correlation objective for self-distilled pruning} implicitly …
The growing size of neural language models has led to increased attention in model compression. The two predominant approaches are pruning, which gradually removes weights from a pre-trained model, and distillation, which trains a smaller compact model to match a larger one. Pruning methods can significantly reduce the model size but hardly achieve large speedups as distillation. However, distillation methods require large amounts of unlabeled data and are expensive to train. In this work, we propose a task-specific structured pruning method CoFi (Coarse- and Fine-grained Pruning), which deliv…
New Jersey Institute of Technology（新泽西理工学院）；Microsoft Research（微软研究院）；Rice University（莱斯大学）
Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks. However, very few of these studies have analyzed the impact of compression on the generalizability and robustness of compressed models for out-of-distribution (OOD) data. Towards this end, we study two popular model compression techniques including knowledge distillation and pruning and show that the compressed models are significantly less robust than their PLM counterparts on OOD test sets although they obtain simi…
In recent years, the growing size of neural networks has led to a vast amount of research concerning compression techniques to mitigate the drawbacks of such large sizes. Most of these research works can be categorized into three broad families : Knowledge Distillation, Pruning, and Quantization. While there has been steady research in this domain, adoption and commercial usage of the proposed techniques has not quite progressed at the rate. We present KD-Lib, an open-source PyTorch based library, which contains state-of-the-art modular implementations of algorithms from the three families on …
Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in performance. However, we argue that conventional methods for retraining pruned networks (i.e., using small, fixed learning rate) are inadequate as they completely ignore the benefits from snapshots of iterative pruning. In this work, we show that strong ensembles can be constructed from snapshots of iterative pruning, which achieve competitive performance and va…
Qualcomm Technologies, Inc.（高通技术公司）；Qualcomm AI Research（高通人工智能研究院）
As edge devices become prevalent, deploying Deep Neural Networks (DNN) on edge devices has become a critical issue. However, DNN requires a high computational resource which is rarely available for edge devices. To handle this, we propose a novel model compression method for the devices with limited computational resources, called PQK consisting of pruning, quantization, and knowledge distillation (KD) processes. Unlike traditional pruning and KD, PQK makes use of unimportant weights pruned in the pruning process to make a teacher network for training a better student network without pre-train…
Network pruning and knowledge distillation are two widely-known model compression methods that efficiently reduce computation cost and model size. A common problem in both pruning and distillation is to determine compressed architecture, i.e., the exact number of filters per layer and layer configuration, in order to preserve most of the original model capacity. In spite of the great advances in existing works, the determination of an excellent architecture still requires human interference or tremendous experimentations. In this paper, we propose an architecture slimming method that automates…
Neural network pruning reduces the computational cost of an over-parameterized network to improve its efficiency. Popular methods vary from $\ell_1$-norm sparsification to Neural Architecture Search (NAS). In this work, we propose a novel pruning method that optimizes the final accuracy of the pruned network and distills knowledge from the over-parameterized parent network's inner layers. To enable this approach, we formulate the network pruning as a Knapsack Problem which optimizes the trade-off between the importance of neurons and their associated computational cost. Then we prune the netwo…
University of Connecticut（康涅狄格大学）；Penn State University（宾夕法尼亚州立大学）；Moffett AI（莫菲特人工智能公司）；Northeastern University（东北大学）；Stevens Institute of Technology（史蒂文斯理工学院）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
Conventional wisdom in pruning Transformer-based language models is that pruning reduces the model expressiveness and thus is more likely to underfit rather than overfit. However, under the trending pretrain-and-finetune paradigm, we postulate a counter-traditional hypothesis, that is: pruning increases the risk of overfitting when performed at the fine-tuning phase. In this paper, we aim to address the overfitting problem and improve pruning performance via progressive knowledge distillation with error-bound properties. We show for the first time that reducing the risk of overfitting can help…
Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning
School of Data Science, Fudan University（复旦大学数据科学学院）；Faculty of Engineering, The Chinese University of Hong Kong（香港中文大学工程学院）；College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）
DeepOpinion（DeepOpinion公司）；University of Innsbruck（因斯布鲁克大学）
Fine-tuning transformer models after unsupervised pre-training reaches a very high performance on many different natural language processing tasks. Unfortunately, transformers suffer from long inference times which greatly increases costs in production. One possible solution is to use knowledge distillation, which solves this problem by transferring information from large teacher models to smaller student models. Knowledge distillation maintains high performance and reaches high compression rates, nevertheless, the size of the student model is fixed after pre-training and can not be changed in…
Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression
Department of Computer Science, University of West Florida（计算机科学系，西佛罗里达大学）；Department of Mathematics and Statistics, University of West Florida（数学与统计学系，西佛罗里达大学）；Department of Intelligent Systems and Robotics, University of West Florida（智能系统与机器人系，西佛罗里达大学）；Institute of Human and Machine Cognition（人机认知研究所）；DEVCOM Army Research Laboratory（陆军研究实验室）
Apple（苹果公司）；Cornell Tech（康奈尔大学科技校区）；Massachusetts Institute of Technology（麻省理工学院）
Quantization, knowledge distillation, and magnitude pruning are among the most popular methods for neural network compression in NLP. Independently, these methods reduce model size and can accelerate inference, but their relative benefit and combinatorial interactions have not been rigorously studied. For each of the eight possible subsets of these techniques, we compare accuracy vs. model size tradeoffs across six BERT architecture sizes and eight GLUE tasks. We find that quantization and distillation consistently provide greater benefit than pruning. Surprisingly, except for the pair of prun…
A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学智能科学与工程学院）；Baidu Inc.（百度公司）；Leiden University（莱顿大学）；Pengcheng Laboratory（鹏城实验室）
Texas State University（德克萨斯州立大学）；Illinois Institute of Technology（伊利诺伊理工学院）
In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic bias generated by AI is more abstract and unintuitive therefore more difficult to explain and mitigate. A clear gap exists in the current literature on evaluating and mitigating bias in pruned neural networks. In this work, we strive to tackle the challenging issues of evaluating, mitigating, and explaining induced bias in pruned neural networks. Our paper makes three contribu…
University of Connecticut（康涅狄格大学）；Northeastern University（东北大学）；Syracuse University（雪城大学）；Microsoft Corporation（微软公司）；Stevens Institute of Technology（史蒂文斯理工学院）
Pre-trained large-scale language models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. However, the limited weight storage and computational speed on hardware platforms have impeded the popularity of pre-trained models, especially in the era of edge computing. In this work, we propose an efficient transformer-based large-scale language representation using hardware-friendly block structure pruning. We incorporate the reweighted group Lasso into block-structured pruning for optimization. Besides the significantly reduced weight storage and computat…
A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce environments, transfers the knowledge on individual word representations learned without restrictions. In this paper, inspired by the recent observations that language representations are relatively positioned and have more semantic knowledge as a whole, we present a new knowledge distillation objective for language representation learning that transfers the conte…
Georgia Institute of Technology（佐治亚理工学院）；Amazon（亚马逊）
Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a compact pre-trained model that can be easily fine-tuned on various tasks with small computational costs and memory footprints. Despite the practical benefits, task-agnostic distillation is challenging. Since the teacher model has a significantly larger capacity and stronger representation power than the student model, it is very difficult for the student to produce predictions t…
To put a state-of-the-art neural network to practical use, it is necessary to design a model that has a good trade-off between the resource consumption and performance on the test set. Many researchers and engineers are developing methods that enable training or designing a model more efficiently. Developing an efficient model includes several strategies such as network architecture search, pruning, quantization, knowledge distillation, utilizing cheap convolution, regularization, and also includes any craft that leads to a better performance-resource trade-off. When combining these technologi…
Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the requirement of a large training set and the time-consuming training procedure. This paper proposes a novel solution for knowledge distillation from label-free few samples to realize both data efficiency and training/processing efficiency. We treat the original network as "teacher-net" and the compressed network as "student-net". A 1x1 convolution layer is a…
The learning capability of a neural network improves with increasing depth at higher computational costs. Wider layers with dense kernel connectivity patterns furhter increase this cost and may hinder real-time inference. We propose feature map and kernel level pruning for reducing the computational complexity of a deep convolutional neural network. Pruning feature maps reduces the width of a layer and hence does not need any sparse representation. Further, kernel pruning converts the dense connectivity pattern into a sparse one. Due to coarse nature, these pruning granularities can be exploit…
Facebook AI Research（脸书人工智能研究院）；Brown University（布朗大学）
In order to contrast the explosion in size of state-of-the-art machine learning models that can be attributed to the empirical advantages of over-parametrization, and due to the necessity of deploying fast, sustainable, and private on-device models on resource-constrained devices, the community has focused on techniques such as pruning, quantization, and distillation as central strategies for model compression. Towards the goal of facilitating the adoption of a common interface for neural network pruning in PyTorch, this contribution describes the recent addition of the PyTorch torch.nn.utils.…
Neural machine translation (NMT) offers a novel alternative formulation of translation that is potentially simpler than statistical approaches. However to reach competitive performance, NMT models need to be exceedingly large. In this paper we consider applying knowledge distillation approaches (Bucila et al., 2006; Hinton et al., 2015) that have proven successful for reducing the size of neural models in other domains to the problem of NMT. We demonstrate that standard knowledge distillation applied to word-level prediction can be effective for NMT, and also introduce two novel sequence-level…
Neural network pruning is frequently used to compress over-parameterized networks by large amounts, while incurring only marginal drops in generalization performance. However, the impact of pruning on networks that have been highly optimized for efficient inference has not received the same level of attention. In this paper, we analyze the effect of pruning for computer vision, and study state-of-the-art ConvNets, such as the FBNetV3 family of models. We show that model pruning approaches can be used to further optimize networks trained through NAS (Neural Architecture Search). The resulting f…
Compact Bayesian Neural Networks via pruned MCMC sampling
ITTC ARC Centre for Data Analytics for Resources and Environment（ITTC ARC资源与环境数据分析中心）；University of Sydney（悉尼大学）；UNSW Data Science Hub（新南威尔士大学数据科学中心）；University of New South Wales（新南威尔士大学）；Geocoastal Research Group（地理海岸研究组）；Transitional Artificial Intelligence Research Group（过渡人工智能研究组）
Deep neural networks have evolved to become power demanding and consequently difficult to apply to small-size mobile platforms. Network parameter reduction methods have been introduced to systematically deal with the computational and memory complexity of deep networks. We propose to examine the ability of attentive connection pruning to deal with redundancy reduction in neural networks as a contribution to the reduction of computational demand. In this work, we describe a Top-Down attention mechanism that is added to a Bottom-Up feedforward network to select important connections and subseque…
Deep neural networks have achieved impressive performance in many applications but their large number of parameters lead to significant computational and storage overheads. Several recent works attempt to mitigate these overheads by designing compact networks using pruning of connections. However, we observe that most of the existing strategies to design compact networks fail to preserve network robustness against adversarial examples. In this work, we rigorously study the extension of network pruning strategies to preserve both benign accuracy and robustness of a network. Starting with a form…
