While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a simple approach to enable parameter-efficient transfer learning within the pretrain-finetune framework. This approach views finetuning as learning a task-specific diff vector that is applied on top of the pretrained parameter vector, which remains fixed and is shared across different tasks. The diff vector is adaptively pruned during training with a differentiable approximation to the L0-norm penalty to encourage sparsity. Diff pruning becomes parameter-efficient as the number of tasks increases, as it requires storing only the nonzero positions and weights of the diff vector for each task, while the cost of storing the shared pretrained model remains constant. It further does not require access to all tasks during training, which makes it attractive in settings where tasks arrive in stream or the set of tasks is unknown. We find that models finetuned with diff pruning can match the performance of fully finetuned baselines on the GLUE benchmark while only modifying 0.5% of the pretrained model's parameters per task.
The increasing of pre-trained models has significantly facilitated the performance on limited data tasks with transfer learning. However, progress on transfer learning mainly focuses on optimizing the weights of pre-trained models, which ignores the structure mismatch between the model and the target task. This paper aims to improve the transfer performance from another angle - in addition to tuning the weights, we tune the structure of pre-trained models, in order to better match the target task. To this end, we propose TransTailor, targeting at pruning the pre-trained model for improved tran…
University of Chinese Academy of Sciences（中国科学院大学）；Columbia University（哥伦比亚大学）
Deep unsupervised domain adaptation (UDA) has recently received increasing attention from researchers. However, existing methods are computationally intensive due to the computation cost of Convolutional Neural Networks (CNN) adopted by most work. To date, there is no effective network compression method for accelerating these models. In this paper, we propose a unified Transfer Channel Pruning (TCP) approach for accelerating UDA models. TCP is capable of compressing the deep UDA model by pruning less important channels while simultaneously learning transferable features by reducing the cross-…
Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural language processing applications. We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. We give mathematical foundations to the method and compare it to existing zeroth- and first-order pruning methods. Experiments show that when pruning large pretrained language models, movement pruning…
We propose a new gradient-based approach for extracting sub-architectures from a given large model. Contrarily to existing pruning methods, which are unable to disentangle the network architecture and the corresponding weights, our architecture-pruning scheme produces transferable new structures that can be successfully retrained to solve different tasks. We focus on a transfer-learning setup where architectures can be trained on a large data set but very few data points are available for fine-tuning them on new tasks. We define a new gradient-based algorithm that trains architectures of arbit…
Learn it or Leave it: Module Composition and Pruning for Continual Learning
Bosch Center for Artificial Intelligence（博世人工智能中心）；LMU Munich（慕尼黑大学）；Hochschule der Medien（慕尼黑应用科技大学）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用科技大学）
In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities. A mechanism is designed to increase and decrease pruning probabilities based on importance criteria in the training process. Exp…
Recently, a race towards the simplification of deep networks has begun, showing that it is effectively possible to reduce the size of these models with minimal or no performance loss. However, there is a general lack in understanding why these pruning strategies are effective. In this work, we are going to compare and analyze pruned solutions with two different pruning approaches, one-shot and gradual, showing the higher effectiveness of the latter. In particular, we find that gradual pruning allows access to narrow, well-generalizing minima, which are typically ignored when using one-shot app…
Monash University（莫纳什大学）；CSIRO Data61（澳大利亚联邦科学与工业研究组织 Data61）；University of Melbourne（墨尔本大学）
Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many pre-trained Teacher models used in transfer learning are publicly available and maintained by public platforms, increasing their vulnerability to backdoor attacks. In this paper, we demonstrate a backdoor threat to transfer learning tasks on both image and time-series data leveraging the knowledge of publicly accessible Teacher models, aimed at defeating three com…
Northeastern University（东北大学）；MIT-IBM Watson AI Lab, IBM Research（IBM研究院 MIT-IBM沃森人工智能实验室）；United States Federal Aviation Administration（美国联邦航空管理局）
Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of downstream tasks. Along with continuous significant performance improvement, the size and complexity of these pre-trained neural models continue to increase rapidly. Is it possible to compress these large-scale language representation models? How will the pruned language representation affect the downstream multi-task transfer learning objectives? In this paper, we …
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets. Generally, more accurate models on the "upstream" dataset tend to provide better transfer accuracy "downstream". In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset, which have been pruned - that is, compressed by sparsifying their connections. We consider transfer using unstructured pruned models obtained by applying several…
The recently proposed Lottery Ticket Hypothesis of Frankle and Carbin (2019) suggests that the performance of over-parameterized deep networks is due to the random initialization seeding the network with a small fraction of favorable weights. These weights retain their dominant status throughout training -- in a very real sense, this sub-network "won the lottery" during initialization. The authors find sub-networks via unstructured magnitude pruning with 85-95% of parameters removed that train to the same accuracy as the original network at a similar speed, which they call winning tickets. In …
School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology（中国矿业大学计算机科学与技术学院/人工智能学院）；Mine Digitization Engineering Research Center of the Ministry of Education（教育部矿山数字化工程研究中心）；Jiangsu Provincial Industrial Technology Engineering Center for Intelligent Sensing and Emergency IoT in Underground Space（江苏省地下空间智能传感与应急物联网产业技术工程中心）；School of Electrical Engineering and Computer Science, University of Ottawa（渥太华大学电气工程与计算机科学学院）
Pre-trained universal feature extractors, such as BERT for natural language processing and VGG for computer vision, have become effective methods for improving deep learning models without requiring more labeled data. While effective, feature extractors like BERT may be prohibitively large for some deployment scenarios. We explore weight pruning for BERT and ask: how does compression during pre-training affect transfer learning? We find that pruning affects transfer learning in three broad regimes. Low levels of pruning (30-40%) do not affect pre-training loss or transfer to downstream tasks a…
New York University（纽约大学）；SLAC National Accelerator Laboratory（SLAC国家加速器实验室）；Facebook AI Research（Facebook人工智能研究）；CIFAR Azrieli Global Scholar（CIFAR Azrieli全球学者（注：CIFAR为机构，但此处为学者头衔，按要求不提取，仅保留前序明确机构））
We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the inactive neurons and filters of the sparsified network and cause zero deterioration to the performance of previous tasks. In order to deal with the possible compromise between model sparsity and performance, we formalize and incorporate the concept of graceful forgetting: the idea that it is preferable to suffer a small amount of forgetting in a controlled manner if it helps reg…
The success of convolutional neural networks (CNNs) in computer vision applications has been accompanied by a significant increase of computation and memory costs, which prohibits its usage on resource-limited environments such as mobile or embedded devices. To this end, the research of CNN compression has recently become emerging. In this paper, we propose a novel filter pruning scheme, termed structured sparsity regularization (SSR), to simultaneously speedup the computation and reduce the memory overhead of CNNs, which can be well supported by various off-the-shelf deep learning libraries. …
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；WeChat AI, Tencent Inc（腾讯微信人工智能部）
Recent studies on the lottery ticket hypothesis (LTH) show that pre-trained language models (PLMs) like BERT contain matching subnetworks that have similar transfer learning performance as the original PLM. These subnetworks are found using magnitude-based pruning. In this paper, we find that the BERT subnetworks have even more potential than these studies have shown. Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability. Inspired by this, we propose to directly optimize the s…
The Pennsylvania State University（宾夕法尼亚州立大学）；Moffett AI（墨菲特人工智能公司）
Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large for resource-limited deployment scenarios. A thread of research has thus been working on applying network pruning techniques under the pretrain-then-finetune paradigm widely adopted in NLP. However, the existing pruning results on benchmark transformers, such as BERT, are not as remarkable as the pruning results in the literature of convolutional neural networ…
Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
Data Science Center ScaDS.AI, Universität Leipzig（ScaDS.AI数据科学中心，莱比锡大学）；Department of Artificial Intelligence, Fraunhofer Heinrich-Hertz-Institute（人工智能系，弗劳恩霍夫 Heinrich-Hertz 研究所）；Department of Electrical Engineering and Computer Science, Technische Universität Berlin（电气工程与计算机科学系，柏林技术大学）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Centre of eXplainable Artificial Intelligence, Technological University Dublin（可解释人工智能中心，都柏林技术大学）
University of Science and Technology of China（中国科学技术大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Westlake University（西湖大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Tencent（腾讯）
Lifelong learning capabilities are crucial for sentiment classifiers to process continuous streams of opinioned information on the Web. However, performing lifelong learning is non-trivial for deep neural networks as continually training of incrementally available information inevitably results in catastrophic forgetting or interference. In this paper, we propose a novel iterative network pruning with uncertainty regularization method for lifelong sentiment classification (IPRLS), which leverages the principles of network pruning and weight regularization. By performing network pruning with un…
