Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

• URL: http://arxiv.org/abs/2405.07527v1
• Date: Mon, 13 May 2024 07:46:48 GMT
• Title: Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models
• Authors: Yubin Shi, Yixuan Chen, Mingzhi Dong, Xiaochen Yang, Dongsheng Li, Yujiang Wang, Robert P. Dick, Qin Lv, Yingying Zhao, Fan Yang, Tun Lu, Ning Gu, Li Shang,
• Abstract summary: We introduce a novel concept dubbed modular neural tangent kernel (mNTK) We show that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue $lambda_max$. We propose a novel training strategy termed Modular Adaptive Training (MAT) to update those modules with their $lambda_max$ exceeding a dynamic threshold.
• Score: 31.960749305728488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized models to attain a more efficient and fruitful training strategy. Empirical evidence reveals that when scaling down into network modules, such as heads in self-attention models, we can observe varying learning patterns implicitly associated with each module's trainability. To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue $\lambda_{\max}$. A large $\lambda_{\max}$ indicates that the module learns features with better convergence, while those miniature ones may impact generalization negatively. Inspired by the discovery, we propose a novel training strategy termed Modular Adaptive Training (MAT) to update those modules with their $\lambda_{\max}$ exceeding a dynamic threshold selectively, concentrating the model on learning common features and ignoring those inconsistent ones. Unlike most existing training schemes with a complete BP cycle across all network modules, MAT can significantly save computations by its partially-updating strategy and can further improve performance. Experiments show that MAT nearly halves the computational cost of model training and outperforms the accuracy of baselines.

Related papers

• Transferable Post-training via Inverse Value Learning [83.75002867411263]
  We propose modeling changes at the logits level during post-training using a separate neural network (i.e., the value network) After training this network on a small base model using demonstrations, this network can be seamlessly integrated with other pre-trained models during inference. We demonstrate that the resulting value network has broad transferability across pre-trained models of different parameter sizes.
  arXiv  Detail & Related papers  (2024-10-28T13:48:43Z)
• Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models [51.5543321122664]
  This paper investigates how to better leverage large-scale pre-trained uni-modal models to enhance discriminative multi-modal learning. We introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA)
  arXiv  Detail & Related papers  (2023-10-08T15:01:54Z)
• Sparse Modular Activation for Efficient Sequence Modeling [94.11125833685583]
  Recent models combining Linear State Space Models with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. Current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. We introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely activate sub-modules for sequence elements in a differentiable manner.
  arXiv  Detail & Related papers  (2023-06-19T23:10:02Z)
• Modularizing while Training: A New Paradigm for Modularizing DNN Models [20.892788625187702]
  We propose a novel approach that incorporates modularization into the model training process, i.e., modularizing-while-training (MwT) The accuracy loss caused by MwT is only 1.13 percentage points, which is 1.76 percentage points less than that of the baseline. The total time cost required for training and modularizing is only 108 minutes, half of the baseline.
  arXiv  Detail & Related papers  (2023-06-15T07:45:43Z)
• ModuleFormer: Modularity Emerges from Mixture-of-Experts [60.6148988099284]
  This paper proposes a new neural network architecture, ModuleFormer, to improve the efficiency and flexibility of large language models. Unlike the previous SMoE-based modular language model, ModuleFormer can induce modularity from uncurated data.
  arXiv  Detail & Related papers  (2023-06-07T17:59:57Z)
• Bulk-Switching Memristor-based Compute-In-Memory Module for Deep Neural Network Training [15.660697326769686]
  We propose a mixed-precision training scheme for memristor-based compute-in-memory (CIM) modules. The proposed scheme is implemented with a system-on-chip (SoC) of fully integrated analog CIM modules and digital sub-systems. The efficacy of training larger models is evaluated using realistic hardware parameters and shows that analog CIM modules can enable efficient mix-precision training with accuracy comparable to full-precision software trained models.
  arXiv  Detail & Related papers  (2023-05-23T22:03:08Z)
• Modular Deep Learning [120.36599591042908]
  Transfer learning has recently become the dominant paradigm of machine learning. It remains unclear how to develop models that specialise towards multiple tasks without incurring negative interference. Modular deep learning has emerged as a promising solution to these challenges.
  arXiv  Detail & Related papers  (2023-02-22T18:11:25Z)
• MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning [68.12870241637636]
  We propose MILO, a model-agnostic subset selection framework that decouples the subset selection from model training. Our empirical results indicate that MILO can train models $3times - 10 times$ faster and tune hyperparameters $20times - 75 times$ faster than full-dataset training or tuning without performance.
  arXiv  Detail & Related papers  (2023-01-30T20:59:30Z)
• Deep Model Assembling [31.88606253639418]
  This paper studies a divide-and-conquer strategy to train large models. It divides a large model into smaller modules, training them independently, and reassembling the trained modules to obtain the target model. We introduce a global, shared meta model to implicitly link all the modules together. This enables us to train highly compatible modules that collaborate effectively when they are assembled together.
  arXiv  Detail & Related papers  (2022-12-08T08:04:06Z)
• Neural Network Module Decomposition and Recomposition [35.21448933547118]
  We propose a modularization method that decomposes a deep neural network (DNN) into small modules from a functionality perspective. We demonstrate that the proposed method can decompose and recompose DNNs with high compression ratio and high accuracy.
  arXiv  Detail & Related papers  (2021-12-25T08:36:47Z)

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.