Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers

• URL: http://arxiv.org/abs/2305.18382v2
• Date: Wed, 12 Jun 2024 08:25:39 GMT
• Title: Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers
• Authors: Zahra Atashgahi, Mykola Pechenizkiy, Raymond Veldhuis, Decebal Constantin Mocanu,
• Abstract summary: We propose textbfAdaptive textbfSparsity textbfLevel (textbfPALS) to automatically seek a decent balance between loss and sparsity. PALS draws inspiration from sparse training and during-training methods. It introduces the novel "expand" mechanism in training sparse neural networks, allowing the model to dynamically shrink, expand, or remain stable to find a proper sparsity level.
• Score: 20.23085795744602
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Efficient time series forecasting has become critical for real-world applications, particularly with deep neural networks (DNNs). Efficiency in DNNs can be achieved through sparse connectivity and reducing the model size. However, finding the sparsity level automatically during training remains challenging due to the heterogeneity in the loss-sparsity tradeoffs across the datasets. In this paper, we propose \enquote{\textbf{P}runing with \textbf{A}daptive \textbf{S}parsity \textbf{L}evel} (\textbf{PALS}), to automatically seek a decent balance between loss and sparsity, all without the need for a predefined sparsity level. PALS draws inspiration from sparse training and during-training methods. It introduces the novel "expand" mechanism in training sparse neural networks, allowing the model to dynamically shrink, expand, or remain stable to find a proper sparsity level. In this paper, we focus on achieving efficiency in transformers known for their excellent time series forecasting performance but high computational cost. Nevertheless, PALS can be applied directly to any DNN. To this aim, we demonstrate its effectiveness also on the DLinear model. Experimental results on six benchmark datasets and five state-of-the-art (SOTA) transformer variants show that PALS substantially reduces model size while maintaining comparable performance to the dense model. More interestingly, PALS even outperforms the dense model, in \textcolor{blue}{12} and \textcolor{blue}{14} cases out of 30 cases in terms of MSE and MAE loss, respectively, while reducing \textcolor{blue}{65\%} parameter count and \textcolor{blue}{63\%} FLOPs on average. Our code and supplementary material are available on Github\footnote{\tiny \url{https://github.com/zahraatashgahi/PALS}}.

Related papers

• Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers [16.253898272659242]
  State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter count and computational costs without significantly impacting their performance. We consider three candidate linear layer approximations in the FFN by combining efficient low-rank and block-diagonal matrices.
  arXiv  Detail & Related papers  (2024-06-24T08:43:21Z)
• From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers [52.199303258423306]
  We propose a novel density loss that encourages higher activation sparsity in pre-trained models. Our proposed method, textbfDEFT, can consistently reduce activation density by up to textbf44.94% on RoBERTa$_mathrmLarge$ and by textbf53.19% (encoder density) and textbf90.60% (decoder density) on Flan-T5$_mathrmXXL$.
  arXiv  Detail & Related papers  (2024-02-02T21:25:46Z)
• Multicoated and Folded Graph Neural Networks with Strong Lottery Tickets [3.0894823679470087]
  This paper introduces the Multi-Stage Folding and Unshared Masks methods to expand the search space in terms of both architecture and parameters. By achieving high sparsity, competitive performance, and high memory efficiency with up to 98.7% reduction, it demonstrates suitability for energy-efficient graph processing.
  arXiv  Detail & Related papers  (2023-12-06T02:16:44Z)
• FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization [5.182014186927254]
  Federated Learning (FL) has been successfully adopted for distributed training and inference of large-scale Deep Neural Networks (DNNs) We contribute with a novel FL framework (coined FedDIP) which combines (i) dynamic model pruning with error feedback to eliminate redundant information exchange. We provide convergence analysis of FedDIP and report on a comprehensive performance and comparative assessment against state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-13T08:51:19Z)
• Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model [92.55145016562867]
  We propose a new family of unbiased estimators called WTA-CRS, for matrix production with reduced variance. Our work provides both theoretical and experimental evidence that, in the context of tuning transformers, our proposed estimators exhibit lower variance compared to existing ones.
  arXiv  Detail & Related papers  (2023-05-24T15:52:08Z)
• Phantom Embeddings: Using Embedding Space for Model Regularization in Deep Neural Networks [12.293294756969477]
  The strength of machine learning models stems from their ability to learn complex function approximations from data. The complex models tend to memorize the training data, which results in poor regularization performance on test data. We present a novel approach to regularize the models by leveraging the information-rich latent embeddings and their high intra-class correlation.
  arXiv  Detail & Related papers  (2023-04-14T17:15:54Z)
• LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time [57.52251547365967]
  We propose a method for training a "compressible subspace" of neural networks that contains a fine-grained spectrum of models. We present results for achieving arbitrarily fine-grained accuracy-efficiency trade-offs at inference time for structured and unstructured sparsity. Our algorithm extends to quantization at variable bit widths, achieving accuracy on par with individually trained networks.
  arXiv  Detail & Related papers  (2021-10-08T17:03:34Z)
• Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation [46.733644368276764]
  We introduce an end-to-end SLT model that does not entail explicit use of glosses. This is in stark contrast to existing end-to-end models that use gloss sequence groundtruth. We demonstrate that our approach can reach the currently best reported BLEU-4 score on the ENIX 2014T benchmark.
  arXiv  Detail & Related papers  (2021-09-01T15:00:52Z)
• 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)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.