Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity

• URL: http://arxiv.org/abs/2410.06846v1
• Date: Wed, 9 Oct 2024 13:06:43 GMT
• Title: Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity
• Authors: Mutian He, Philip N. Garner,
• Abstract summary: We present a Cross-Architecture Layerwise Distillation (CALD) approach that jointly converts a transformer model to a linear time substitute and fine-tunes it to a target task. We show that CALD can effectively recover the result of the original model, and that the guiding strategy contributes to the result.
• Score: 11.302828987873497
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Architectures such as Linformer and Mamba have recently emerged as competitive linear time replacements for transformers. However, corresponding large pretrained models are often unavailable, especially in non-text domains. To remedy this, we present a Cross-Architecture Layerwise Distillation (CALD) approach that jointly converts a transformer model to a linear time substitute and fine-tunes it to a target task. We also compare several means to guide the fine-tuning to optimally retain the desired inference capability from the original model. The methods differ in their use of the target model and the trajectory of the parameters. In a series of empirical studies on language processing, language modeling, and speech processing, we show that CALD can effectively recover the result of the original model, and that the guiding strategy contributes to the result. Some reasons for the variation are suggested.

Related papers

• Meta-Learning Adaptable Foundation Models [37.458141335750696]
  We introduce a meta-learning framework infused with PEFT in this intermediate retraining stage to learn a model that can be easily adapted to unseen tasks. In this setting, we demonstrate the suboptimality of standard retraining for finding an adaptable set of parameters. We then apply these theoretical insights to retraining the RoBERTa model to predict the continuation of conversations within the ConvAI2 dataset.
  arXiv  Detail & Related papers  (2024-10-29T17:24:18Z)
• Demystifying the Communication Characteristics for Distributed Transformer Models [2.849208476795592]
  This paper examines the communication behavior of transformer models. We use GPT-based language models as a case study of the transformer architecture due to their ubiquity. At a high level, our analysis reveals a need to optimize small message point-to-point communication further.
  arXiv  Detail & Related papers  (2024-08-19T17:54:29Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Probabilistic Topic Modelling with Transformer Representations [0.9999629695552195]
  We propose the Transformer-Representation Neural Topic Model (TNTM) This approach unifies the powerful and versatile notion of topics based on transformer embeddings with fully probabilistic modelling. Experimental results show that our proposed model achieves results on par with various state-of-the-art approaches in terms of embedding coherence.
  arXiv  Detail & Related papers  (2024-03-06T14:27:29Z)
• Merging Text Transformer Models from Different Initializations [7.768975909119287]
  We investigate the extent to which separate Transformer minima learn similar features. We propose a model merging technique to investigate the relationship between these minima in the loss landscape. Our results show that the minima of these models are less sharp and isolated than previously understood.
  arXiv  Detail & Related papers  (2024-03-01T21:16:29Z)
• N-Grammer: Augmenting Transformers with latent n-grams [35.39961549040385]
  We propose a simple yet effective modification to the Transformer architecture inspired by the literature in statistical language modeling, by augmenting the model with n-grams that are constructed from a discrete latent representation of the text sequence. We evaluate our model, the N-Grammer on language modeling on the C4 data-set as well as text classification on the SuperGLUE data-set, and find that it outperforms several strong baselines such as the Transformer and the Primer.
  arXiv  Detail & Related papers  (2022-07-13T17:18:02Z)
• Factorized Neural Transducer for Efficient Language Model Adaptation [51.81097243306204]
  We propose a novel model, factorized neural Transducer, by factorizing the blank and vocabulary prediction. It is expected that this factorization can transfer the improvement of the standalone language model to the Transducer for speech recognition. We demonstrate that the proposed factorized neural Transducer yields 15% to 20% WER improvements when out-of-domain text data is used for language model adaptation.
  arXiv  Detail & Related papers  (2021-09-27T15:04:00Z)
• Decision Transformer: Reinforcement Learning via Sequence Modeling [102.86873656751489]
  We present a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. We present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling. Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.
  arXiv  Detail & Related papers  (2021-06-02T17:53:39Z)
• Bayesian Transformer Language Models for Speech Recognition [59.235405107295655]
  State-of-the-art neural language models (LMs) represented by Transformers are highly complex. This paper proposes a full Bayesian learning framework for Transformer LM estimation.
  arXiv  Detail & Related papers  (2021-02-09T10:55:27Z)
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling [54.94763543386523]
  Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the ( aggregate) posterior to encourage statistical independence of the latent factors. We present a novel multi-stage modeling approach where the disentangled factors are first learned using a penalty-based disentangled representation learning method. Then, the low-quality reconstruction is improved with another deep generative model that is trained to model the missing correlated latent variables.
  arXiv  Detail & Related papers  (2020-10-25T18:51:15Z)
• Haar Wavelet based Block Autoregressive Flows for Trajectories [129.37479472754083]
  Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. We introduce a novel Haar wavelet based block autoregressive model leveraging split couplings. We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets.
  arXiv  Detail & Related papers  (2020-09-21T13:57:10Z)

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.