A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to accelerate inference speed of pre-trained language models are limited to local representations of exit layer . current models are associated with large memory requirement and high computational cost, which slow down inference and further encumber the application of PLMs. |
| Approach: | They propose a method to exit early without passing through all inference layers . they take into consideration all the linguistic information embedded in the past layers a global perspective . |
| Outcome: | The proposed method outperforms existing methods by a large margin . it uses linguistic information embedded in the past layers and future features . the proposed method is scalable and cost-effective . |
Similar Papers
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that CascadeBERT can achieve an overall 15% improvement under 4x speed-up compared with existing dynamic early exiting methods on six classification tasks. |
| Approach: | They propose a framework which emits predictions in internal layers without passing through the entire model. |
| Outcome: | The proposed framework can achieve 15% improvement under 4x speed-up compared with existing methods on six classification tasks yielding more calibrated and accurate predictions. |
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to speed up inference latency have shown performance degradation caused by a state copying mechanism or numerous exit paths. |
| Approach: | They propose a framework that allocates adaptive computation paths for each token based on the complexity of generating the subsequent token. |
| Outcome: | The proposed framework outperforms existing frameworks on extensive generation tasks. |
A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation (2022.findings-acl)
Copied to clipboard
Tianxiang Sun, Xiangyang Liu, Wei Zhu, Zhichao Geng, Lingling Wu, Yilong He, Yuan Ni, Guotong Xie, Xuanjing Huang, Xipeng Qiu
| Challenge: | Existing methods to measure instance difficulty use generalization and threshold-tuning . a new approach to learn to exit is based on hash functions to assign tokens to a fixed exiting layer. |
| Approach: | They propose a Hash-based Early Exiting approach that replaces learn-to-exit modules with hash functions to assign each token to a fixed exiting layer. |
| Outcome: | The proposed approach improves on learning to exit and predicting instance difficulty. |
LECO: Improving Early Exiting via Learned Exits and Comparison-based Exiting Mechanism (2023.acl-srw)
Copied to clipboard
| Challenge: | Recent work on dynamic early exiting has neglected the intermediate exits’ architectural designs. |
| Approach: | They propose a framework for learning exits and COmparison-based early exiting to improve PTMs’ early exit performance. |
| Outcome: | The proposed framework achieves the SOTA performance on multi-exit BERT training and dynamic early exiting on pre-trained models. |
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding (2024.acl-long)
Copied to clipboard
Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil Hosmer, Bram Wasti, Liangzhen Lai, Anas Mahmoud, Bilge Acun, Saurabh Agarwal, Ahmed Roman, Ahmed Aly, Beidi Chen, Carole-Jean Wu
| Challenge: | Large Language Models (LLMs) have been deployed to many applications, yet their high compute and memory requirements lead to high financial and energy costs when deployed to GPU servers. |
| Approach: | They propose an end-to-end solution to speed-up inference of large language models . they apply layer dropout, and show that it increases the accuracy of early exit at earlier layers without adding any auxiliary layers or modules to the model. |
| Outcome: | The proposed method shows speedups of up to 2.16x on summarization for CNN/DM documents, 1.82x on coding, and 2.0x on TOPv2 semantic parsing task. |
Accelerating BERT Inference for Sequence Labeling via Early-Exit (2021.acl-long)
Copied to clipboard
| Challenge: | Existing early-exit mechanisms are designed for sequence-level tasks, rather than sequence labeling. |
| Approach: | They propose to extend sentence-level early-exit to accelerate inference of PTMs . they propose a token-level mechanism that allows partial tokens to exit early at different layers . |
| Outcome: | The proposed approach can save up to 66%75% inference cost with minimal performance degradation. |
Accelerating Inference for Pretrained Language Models by Unified Multi-Perspective Early Exiting (2022.coling-1)
Copied to clipboard
| Challenge: | Existing competitive methods to accelerate inference of pretrained language models are limited by their complexity and computational consumption. |
| Approach: | They propose a unified horizontal and vertical multi-perspective early exiting framework to accelerate inference of transformer-based models. |
| Outcome: | Experiments show that MPEE can achieve higher acceleration inference with competent performance than existing competitive methods. |
LeeBERT: Learned Early Exit for BERT with cross-level optimization (2021.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models are resource exhaustive and computationally expensive for industrial scenarios. |
| Approach: | They propose a learning scheme to learn from each other to speed up inference . they ask each exit to learn the weights of different loss terms, instead of learning only from the last layer . |
| Outcome: | The proposed scheme improves state-of-the-art (SOTA) early exit methods for pre-trained models on the GLUE benchmark. |
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference (2020.acl-main)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models such as BERT are notorious for being slow in both training and inference. |
| Approach: | They propose a method to accelerate BERT inference by inserting extra classification layers between each transformer layer of BERT. |
| Outcome: | The proposed method saves up to 40% inference time with minimal degradation in model quality. |
BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting (2023.acl-industry)
Copied to clipboard
| Challenge: | Recent years have witnessed the rise of many pre-trained language models (PLMs) such as GPT (Radford et al., 2019) and XLNet (Yang e.t al, 2019). |
| Approach: | They propose a framework which consists of two off-the-shelf methods for improving PLMs’ early exiting. |
| Outcome: | The proposed method can reduce the average latency of pre-trained language models and work with other inference speed-up methods like model pruning. |