Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers

• URL: http://arxiv.org/abs/2305.15805v3
• Date: Fri, 31 May 2024 14:02:24 GMT
• Title: Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
• Authors: Sotiris Anagnostidis, Dario Pavllo, Luca Biggio, Lorenzo Noci, Aurelien Lucchi, Thomas Hofmann,
• Abstract summary: We present a novel approach that dynamically prunes contextual information while preserving the model's expressiveness. Our method employs a learnable mechanism that determines which uninformative tokens can be dropped from the context. Our reference implementation achieves up to $2times$ increase in inference throughput and even greater memory savings.
• Score: 29.319666323947708
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens in the sequence, thus incurring a quadratic cost. In this study, we present a novel approach that dynamically prunes contextual information while preserving the model's expressiveness, resulting in reduced memory and computational requirements during inference. Our method employs a learnable mechanism that determines which uninformative tokens can be dropped from the context at any point across the generation process. By doing so, our approach not only addresses performance concerns but also enhances interpretability, providing valuable insight into the model's decision-making process. Our technique can be applied to existing pre-trained models through a straightforward fine-tuning process, and the pruning strength can be specified by a sparsity parameter. Notably, our empirical findings demonstrate that we can effectively prune up to 80\% of the context without significant performance degradation on downstream tasks, offering a valuable tool for mitigating inference costs. Our reference implementation achieves up to $2\times$ increase in inference throughput and even greater memory savings.

Related papers

• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• Rational Metareasoning for Large Language Models [5.5539136805232205]
  Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs) This work introduces a novel approach based on computational models of metareasoning used in cognitive science. We develop a reward function that incorporates the Value of Computation by penalizing unnecessary reasoning.
  arXiv  Detail & Related papers  (2024-10-07T23:48:52Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling [52.404072802235234]
  We introduce Chunked Instruction-aware State Eviction (CItruS), a novel modeling technique that integrates the attention preferences useful for a downstream task into the eviction process of hidden states. Our training-free method exhibits superior performance on long sequence comprehension and retrieval tasks over several strong baselines under the same memory budget.
  arXiv  Detail & Related papers  (2024-06-17T18:34:58Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• Frustratingly Simple Memory Efficiency for Pre-trained Language Models via Dynamic Embedding Pruning [42.652021176354644]
  The memory footprint of pre-trained language models (PLMs) can hinder deployment in memory-constrained settings. We propose a simple yet effective approach that leverages this finding to minimize the memory footprint of the embedding matrix. We show that this approach provides substantial reductions in memory usage across a wide range of models and tasks.
  arXiv  Detail & Related papers  (2023-09-15T19:00:00Z)
• On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers [47.77328392236625]
  State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts. We introduce a two-stage training procedure, where we first optimize the task-specific parameters and then train the classifier with the same selection procedure of the inference time. Our method achieves results that are either superior or on par with the state of the art while being computationally cheaper.
  arXiv  Detail & Related papers  (2023-08-18T15:11:16Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)
• A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation [53.8171136907856]
  We introduce a set of simple yet effective data augmentation strategies dubbed cutoff. cutoff relies on sampling consistency and thus adds little computational overhead. cutoff consistently outperforms adversarial training and achieves state-of-the-art results on the IWSLT2014 German-English dataset.
  arXiv  Detail & Related papers  (2020-09-29T07:08:35Z)

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.