TT-MPD: Test Time Model Pruning and Distillation

• URL: http://arxiv.org/abs/2412.07114v1
• Date: Tue, 10 Dec 2024 02:05:13 GMT
• Title: TT-MPD: Test Time Model Pruning and Distillation
• Authors: Haihang Wu, Wei Wang, Tamasha Malepathirana, Sachith Seneviratne, Denny Oetomo, Saman Halgamuge,
• Abstract summary: Pruning can be an effective method of compressing large pre-trained models for inference speed acceleration. Previous pruning approaches rely on access to the original training dataset for both pruning and subsequent fine-tuning. We propose an efficient pruning method that considers the approximated finetuned accuracy and potential inference latency saving.
• Score: 3.675015670568961
• License:
• Abstract: Pruning can be an effective method of compressing large pre-trained models for inference speed acceleration. Previous pruning approaches rely on access to the original training dataset for both pruning and subsequent fine-tuning. However, access to the training data can be limited due to concerns such as data privacy and commercial confidentiality. Furthermore, with covariate shift (disparities between test and training data distributions), pruning and finetuning with training datasets can hinder the generalization of the pruned model to test data. To address these issues, pruning and finetuning the model with test time samples becomes essential. However, test-time model pruning and fine-tuning incur additional computation costs and slow down the model's prediction speed, thus posing efficiency issues. Existing pruning methods are not efficient enough for test time model pruning setting, since finetuning the pruned model is needed to evaluate the importance of removable components. To address this, we propose two variables to approximate the fine-tuned accuracy. We then introduce an efficient pruning method that considers the approximated finetuned accuracy and potential inference latency saving. To enhance fine-tuning efficiency, we propose an efficient knowledge distillation method that only needs to generate pseudo labels for a small set of finetuning samples one time, thereby reducing the expensive pseudo-label generation cost. Experimental results demonstrate that our method achieves a comparable or superior tradeoff between test accuracy and inference latency, with a 32% relative reduction in pruning and finetuning time compared to the best existing method.

Related papers

• PUMA: margin-based data pruning [51.12154122266251]
  We focus on data pruning, where some training samples are removed based on the distance to the model classification boundary (i.e., margin) We propose PUMA, a new data pruning strategy that computes the margin using DeepFool. We show that PUMA can be used on top of the current state-of-the-art methodology in robustness, and it is able to significantly improve the model performance unlike the existing data pruning strategies.
  arXiv  Detail & Related papers  (2024-05-10T08:02:20Z)
• Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting [55.17761802332469]
  Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample. Prior methods perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications. We propose an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples.
  arXiv  Detail & Related papers  (2024-03-18T05:49:45Z)
• Distilling the Knowledge in Data Pruning [4.720247265804016]
  We explore the application of data pruning while incorporating knowledge distillation (KD) when training on a pruned subset. We demonstrate significant improvement across datasets, pruning methods, and on all pruning fractions. We make an intriguing observation: when using lower pruning fractions, larger teachers lead to accuracy degradation, while surprisingly, employing teachers with a smaller capacity than the student's may improve results.
  arXiv  Detail & Related papers  (2024-03-12T17:44:45Z)
• BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping [64.54271680071373]
  Diffusion models have demonstrated excellent potential for generating diverse images. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few. We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
  arXiv  Detail & Related papers  (2023-06-08T20:30:55Z)
• Gradient-Free Structured Pruning with Unlabeled Data [57.999191898036706]
  We propose a gradient-free structured pruning framework that uses only unlabeled data. Up to 40% of the original FLOP count can be reduced with less than a 4% accuracy loss across all tasks considered.
  arXiv  Detail & Related papers  (2023-03-07T19:12:31Z)
• Structured Pruning Learns Compact and Accurate Models [28.54826400747667]
  We propose a task-specific structured pruning method CoFi (Coarse- and Fine-grained Pruning) CoFi delivers highly parallelizableworks and matches the distillation methods in both accuracy and latency. Our experiments on GLUE and SQuAD datasets show that CoFi yields models with over 10x speedups with a small accuracy drop.
  arXiv  Detail & Related papers  (2022-04-01T13:09:56Z)
• Combined Pruning for Nested Cross-Validation to Accelerate Automated Hyperparameter Optimization for Embedded Feature Selection in High-Dimensional Data with Very Small Sample Sizes [3.51500332842165]
  Tree-based embedded feature selection to exclude irrelevant features in high-dimensional data with very small sample sizes requires optimized hyperparameters for the model building process. Standard pruning algorithms must prune late or risk aborting calculations due to high variance in the performance evaluation metric. We adapt the usage of a state-of-the-art successive halving pruner and combine it with two new pruning strategies based on domain or prior knowledge. Our proposed combined three-layer pruner keeps promising trials while reducing the number of models to be built by up to 81,3% compared to using a state-of-the-
  arXiv  Detail & Related papers  (2022-02-01T17:42:37Z)
• Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay [5.3330804968579795]
  Data-Free Knowledge Distillation (KD) allows knowledge transfer from a trained neural network (teacher) to a more compact one (student) in the absence of original training data. Existing works use a validation set to monitor the accuracy of the student over real data and report the highest performance throughout the entire process. However, validation data may not be available at distillation time either, making it infeasible to record the student snapshot that achieved the peak accuracy. This is challenging because the student experiences knowledge degradation due to the distribution shift of the synthetic data. We propose to model the distribution of the previously observed synthetic samples
  arXiv  Detail & Related papers  (2022-01-09T14:14:28Z)
• Block Pruning For Faster Transformers [89.70392810063247]
  We introduce a block pruning approach targeting both small and fast models. We find that this approach learns to prune out full components of the underlying model, such as attention heads.
  arXiv  Detail & Related papers  (2021-09-10T12:46:32Z)
• The Right Tool for the Job: Matching Model and Instance Complexities [62.95183777679024]
  As NLP models become larger, executing a trained model requires significant computational resources incurring monetary and environmental costs. We propose a modification to contextual representation fine-tuning which, during inference, allows for an early (and fast) "exit" We test our proposed modification on five different datasets in two tasks: three text classification datasets and two natural language inference benchmarks.
  arXiv  Detail & Related papers  (2020-04-16T04:28:08Z)

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.