Adapting by Pruning: A Case Study on BERT

• URL: http://arxiv.org/abs/2105.03343v1
• Date: Fri, 7 May 2021 15:51:08 GMT
• Title: Adapting by Pruning: A Case Study on BERT
• Authors: Yang Gao and Nicolo Colombo and Wei Wang
• Abstract summary: We propose a novel model adaptation paradigm, adapting by pruning, which prunes neural connections in the pre-trained model to optimise the performance on the target task. We formulate adapting-by-pruning as an optimisation problem with a differentiable loss and propose an efficient algorithm to prune the model. Results suggest that our method can prune up to 50% weights in BERT while yielding similar performance compared to the fine-tuned full model.
• Score: 9.963251767416967
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models. In this work, we propose a novel model adaptation paradigm, adapting by pruning, which prunes neural connections in the pre-trained model to optimise the performance on the target task; all remaining connections have their weights intact. We formulate adapting-by-pruning as an optimisation problem with a differentiable loss and propose an efficient algorithm to prune the model. We prove that the algorithm is near-optimal under standard assumptions and apply the algorithm to adapt BERT to some GLUE tasks. Results suggest that our method can prune up to 50% weights in BERT while yielding similar performance compared to the fine-tuned full model. We also compare our method with other state-of-the-art pruning methods and study the topological differences of their obtained sub-networks.

Related papers

• MARS: Unleashing the Power of Variance Reduction for Training Large Models [56.47014540413659]
  Large gradient algorithms like Adam, Adam, and their variants have been central to the development of this type of training. We propose a framework that reconciles preconditioned gradient optimization methods with variance reduction via a scaled momentum technique.
  arXiv  Detail & Related papers  (2024-11-15T18:57:39Z)
• NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval [0.7646713951724011]
  Existing approaches either fine-tune the pre-trained model itself or, more efficiently, train adaptor models to transform the output of the pre-trained model. We present NUDGE, a family of novel non-parametric embedding fine-tuning approaches. NUDGE directly modifies the embeddings of data records to maximize the accuracy of $k$-NN retrieval.
  arXiv  Detail & Related papers  (2024-09-04T00:10:36Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Adaptive Sparse Gaussian Process [0.0]
  We propose the first adaptive sparse Gaussian Process (GP) able to address all these issues. We first reformulate a variational sparse GP algorithm to make it adaptive through a forgetting factor. We then propose updating a single inducing point of the sparse GP model together with the remaining model parameters every time a new sample arrives.
  arXiv  Detail & Related papers  (2023-02-20T21:34:36Z)
• Faster Adaptive Federated Learning [84.38913517122619]
  Federated learning has attracted increasing attention with the emergence of distributed data. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on momentum-based variance reduced technique in cross-silo FL.
  arXiv  Detail & Related papers  (2022-12-02T05:07:50Z)
• Robust Binary Models by Pruning Randomly-initialized Networks [57.03100916030444]
  We propose ways to obtain robust models against adversarial attacks from randomly-d binary networks. We learn the structure of the robust model by pruning a randomly-d binary network. Our method confirms the strong lottery ticket hypothesis in the presence of adversarial attacks.
  arXiv  Detail & Related papers  (2022-02-03T00:05:08Z)
• Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
  We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models. Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-18T01:03:13Z)
• Adaptive Sampling for Minimax Fair Classification [40.936345085421955]
  We propose an adaptive sampling algorithm based on the principle of optimism, and derive theoretical bounds on its performance. By deriving algorithm independent lower-bounds for a specific class of problems, we show that the performance achieved by our adaptive scheme cannot be improved in general.
  arXiv  Detail & Related papers  (2021-03-01T04:58:27Z)
• Evolutionary Variational Optimization of Generative Models [0.0]
  We combine two popular optimization approaches to derive learning algorithms for generative models: variational optimization and evolutionary algorithms. We show that evolutionary algorithms can effectively and efficiently optimize the variational bound. In the category of "zero-shot" learning, we observed the evolutionary variational algorithm to significantly improve the state-of-the-art in many benchmark settings.
  arXiv  Detail & Related papers  (2020-12-22T19:06:33Z)
• Neural Model-based Optimization with Right-Censored Observations [42.530925002607376]
  Neural networks (NNs) have been demonstrated to work well at the core of model-based optimization procedures. We show that our trained regression models achieve a better predictive quality than several baselines.
  arXiv  Detail & Related papers  (2020-09-29T07:32:30Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

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.