BEExformer: A Fast Inferencing Binarized Transformer with Early Exits

• URL: http://arxiv.org/abs/2412.05225v2
• Date: Sat, 12 Jul 2025 18:28:38 GMT
• Title: BEExformer: A Fast Inferencing Binarized Transformer with Early Exits
• Authors: Wazib Ansar, Saptarsi Goswami, Amlan Chakrabarti,
• Abstract summary: We introduce Binarized Early Exit Transformer (BEExformer), the first-ever selective learning-based transformer integrating Binarization-Aware Training (BAT) with Early Exit (EE)<n>BAT employs a differentiable second-order approximation to the sign function, enabling gradient that captures both the sign and magnitude of the weights.<n>EE mechanism hinges on fractional reduction in entropy among intermediate transformer blocks with soft-routing loss estimation.<n>This accelerates inference by reducing FLOPs by 52.08% and even improves accuracy by 2.89% by resolving the "overthinking" problem inherent in deep networks.
• Score: 2.7651063843287718
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Language Models (LLMs) based on transformers achieve cutting-edge results on a variety of applications. However, their enormous size and processing requirements hinder deployment on constrained resources. To enhance efficiency, binarization and Early Exit (EE) have proved to be effective solutions. However, binarization may lead to performance loss as reduced precision affects gradient estimation and parameter updates. Besides, research on EE mechanisms is still in its early stages. To address these challenges, we introduce Binarized Early Exit Transformer (BEExformer), the first-ever selective learning-based transformer integrating Binarization-Aware Training (BAT) with EE for efficient and fast textual inference. Each transformer block has an integrated Selective-Learn Forget Network (SLFN) to enhance contextual retention while eliminating irrelevant information. The BAT employs a differentiable second-order approximation to the sign function, enabling gradient computation that captures both the sign and magnitude of the weights. This aids in 21.30 times reduction in model size. The EE mechanism hinges on fractional reduction in entropy among intermediate transformer blocks with soft-routing loss estimation. This accelerates inference by reducing FLOPs by 52.08% and even improves accuracy by 2.89% by resolving the "overthinking" problem inherent in deep networks. Extensive evaluation through comparison with the SOTA methods and various ablations across six datasets covering multiple NLP tasks demonstrates its Pareto-optimal performance-efficiency trade-off.

Related papers

• Energy-Based Transformers are Scalable Learners and Thinkers [84.7474634026213]
  Energy-Based Transformers (EBTs) are a new class of Energy-Based Models (EBMs)<n>We train EBTs to assign an energy value to every input and candidate-prediction pair, enabling predictions through gradient descent-based energy until convergence.<n>During inference, EBTs improve performance with System 2 Thinking by 29% more than the Transformer++ on language tasks.
  arXiv  Detail & Related papers  (2025-07-02T19:17:29Z)
• Revisiting Funnel Transformers for Modern LLM Architectures with Comprehensive Ablations in Training and Inference Configurations [1.6255281211429766]
  We investigate the impact of funneling in contemporary Gemma2 Transformer architectures. We find that funneling creates information bottlenecks that propagate through deeper network layers, particularly in larger models. Our findings highlight key trade-offs between computational efficiency and model accuracy.
  arXiv  Detail & Related papers  (2025-04-02T02:09:17Z)
• BHViT: Binarized Hybrid Vision Transformer [53.38894971164072]
  Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN) We propose BHViT, a binarization-friendly hybrid ViT architecture and its full binarization model with the guidance of three important observations. Our proposed algorithm achieves SOTA performance among binary ViT methods.
  arXiv  Detail & Related papers  (2025-03-04T08:35:01Z)
• Transformer Meets Twicing: Harnessing Unattended Residual Information [2.1605931466490795]
  Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks.<n>While the self-attention mechanism has proven capable of handling complex data patterns, it has been observed that the representational capacity of the attention matrix degrades significantly across transformer layers.<n>We propose the Twicing Attention, a novel attention mechanism that uses kernel twicing procedure in nonparametric regression to alleviate the low-pass behavior of associated NLM smoothing.
  arXiv  Detail & Related papers  (2025-03-02T01:56:35Z)
• Joint Transmit and Pinching Beamforming for Pinching Antenna Systems (PASS): Optimization-Based or Learning-Based? [89.05848771674773]
  A novel antenna system ()-enabled downlink multi-user multiple-input single-output (MISO) framework is proposed. It consists of multiple waveguides, which equip numerous low-cost antennas, named (PAs) The positions of PAs can be reconfigured to both spanning large-scale path and space.
  arXiv  Detail & Related papers  (2025-02-12T18:54:10Z)
• Binary Event-Driven Spiking Transformer [36.815359983551986]
  Transformer-based Spiking Neural Networks (SNNs) introduce a novel event-driven self-attention paradigm.<n>We propose the Binary Event-Driven Spiking Transformer, i.e. BESTformer.<n> BESTformer suffers from a severe performance drop from its full-precision counterpart due to the limited representation capability of binarization.
  arXiv  Detail & Related papers  (2025-01-10T12:00:11Z)
• Re-Parameterization of Lightweight Transformer for On-Device Speech Emotion Recognition [10.302458835329539]
  We introduce a new method, namely Transformer Re- parameterization, to boost the performance of lightweight Transformer models. Experimental results show that our proposed method consistently improves the performance of lightweight Transformers, even making them comparable to large models.
  arXiv  Detail & Related papers  (2024-11-14T10:36:19Z)
• 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)
• DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization [12.277820111814691]
  DSFormer is a simple alternative factorization scheme which expresses a target weight matrix as the product of a small dense and a semi-structured sparse matrix. Our approach is also to mainstream compressors and offers up to 50% additional compression when added to popular distilled, layer-shared and quantized transformers.
  arXiv  Detail & Related papers  (2023-12-20T17:27:25Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)
• GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples [46.025105938192624]
  Vision Transformer (ViT) has performed remarkably in various computer vision tasks. ViT usually suffers from serious overfitting problems with a relatively limited number of training samples. We propose a novel model binarization technique, called Group Superposition Binarization (GSB)
  arXiv  Detail & Related papers  (2023-05-13T14:48:09Z)
• HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression [69.36555801766762]
  We propose a hardware-aware tensor decomposition framework, dubbed HEAT, that enables efficient exploration of the exponential space of possible decompositions. We experimentally show that our hardware-aware factorized BERT variants reduce the energy-delay product by 5.7x with less than 1.1% accuracy loss.
  arXiv  Detail & Related papers  (2022-11-30T05:31:45Z)
• Magic ELF: Image Deraining Meets Association Learning and Transformer [63.761812092934576]
  This paper aims to unify CNN and Transformer to take advantage of their learning merits for image deraining. A novel multi-input attention module (MAM) is proposed to associate rain removal and background recovery. Our proposed method (dubbed as ELF) outperforms the state-of-the-art approach (MPRNet) by 0.25 dB on average.
  arXiv  Detail & Related papers  (2022-07-21T12:50:54Z)
• Efficient Decoder-free Object Detection with Transformers [75.00499377197475]
  Vision transformers (ViTs) are changing the landscape of object detection approaches. We propose a decoder-free fully transformer-based (DFFT) object detector. DFFT_SMALL achieves high efficiency in both training and inference stages.
  arXiv  Detail & Related papers  (2022-06-14T13:22:19Z)
• Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT [22.904252855587348]
  We propose a fine- and coarse-granularity hybrid self-attention that reduces the cost through progressively shortening the computational sequence length in self-attention. We show that FCA offers a significantly better trade-off between accuracy and FLOPs compared to prior methods.
  arXiv  Detail & Related papers  (2022-03-17T03:33:47Z)
• Latency Adjustable Transformer Encoder for Language Understanding [0.8287206589886879]
  This paper proposes an efficient Transformer architecture that adjusts the inference computational cost adaptively with a desired inference latency speedup. The proposed method detects less important hidden sequence elements (word-vectors) and eliminates them in each encoder layer using a proposed Attention Context Contribution (ACC) metric. The proposed method mathematically and experimentally improves the inference latency of BERT_base and GPT-2 by up to 4.8 and 3.72 times with less than 0.75% accuracy drop and passable perplexity on average.
  arXiv  Detail & Related papers  (2022-01-10T13:04:39Z)
• Efficient pre-training objectives for Transformers [84.64393460397471]
  We study several efficient pre-training objectives for Transformers-based models. We prove that eliminating the MASK token and considering the whole output during the loss are essential choices to improve performance.
  arXiv  Detail & Related papers  (2021-04-20T00:09:37Z)

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.