Recently, the efficient deployment and acceleration of transformer-based pre-trained models (TPMs) on resource-constrained edge devices for multimedia services have gained significant interest. Although early exiting is a feasible solution, it may lead to extra computational cost and substantial performance degradation compared to the original models. To tackle these issues, we propose a framework termed EEformer, which incorporates global-local heads (GLHs) into intermediate layers to construct the early exiting dynamic neural network (EDNN). The GLH can efficiently extract global and local information from hidden states produced by the backbone layer, thereby achieving a better performance-efficiency trade-off for the EDNN. Moreover, we propose a novel progressive fine-tuning strategy to steadily improve the efficiency of the EDNN while maintaining its performance comparable to the original mode through three fine-tuning stages. We conduct extensive experiments on image classification and natural language processing tasks, demonstrating the superiority of the proposed framework. In particular, the proposed framework achieves 1.87× speed-up while maintaining 99.0% performance on the CIFAR-100 dataset, and 3.05× speed-up while maintaining 98.5% performance on the SST-2 dataset.

Semantic communication is a novel communication paradigm that demonstrates great potential in information transmission applications, particularly in challenging scenarios characterized by low signal-to-noise ratio (SNR) conditions. It extracts task-relevant semantic information and performs end-to-end optimization of source and channel coding. However, current mainstream architectures do not account for the importance of features in the subsequent reconstruction process. This shortcoming leads to the transmission of all features, resulting in inefficient bandwidth utilization. Furthermore, existing methods reconstruct all images equally, regardless of their differences in complexity, which is inefficient and wastes computational resources. To address these issues, we develop an efficient semantic communication architecture, termed ESC. Specifically, we design feature selection and reconstruction modules to filter out unimportant information, addressing the problem of transmission feature redundancy and improving bandwidth utilization efficiency. In addition, we develop a multi-branch decoder architecture and an adaptive inference strategy to accommodate the varying complexities of images, allowing samples with satisfactory reconstruction results to exit the decoder network early, thus reducing inference costs. By introducing feature selection, our architecture’s reconstruction quality surpasses that of 5G systems and mainstream semantic communication under the same bandwidth on the Kodak and CLIC2021 datasets. Our adaptive inference strategy achieves speed-ups of approximately 1.37 × and 1.43 × respectively, with only minimal degradation in image reconstruction quality.

The impressive performance of transformer models has sparked the deployment of intelligent applications on resource-constrained edge devices. However, ensuring high-quality service for real-time edge systems is a significant challenge due to the considerable computational demands and resource requirements of these models. Existing strategies typically either offload transformer computations to other devices or directly deploy compressed models on individual edge devices. These strategies, however, result in either considerable communication overhead or suboptimal trade-offs between accuracy and efficiency. To tackle these challenges, we propose a collaborative inference system for general transformer models, termed CoFormer. The central idea behind CoFormer is to exploit the divisibility and integrability of transformer. An off-the-shelf large transformer can be decomposed into multiple smaller models for distributed inference, and their intermediate results are aggregated to generate the final output. We formulate an optimization problem to minimize both inference latency and accuracy degradation under heterogeneous hardware constraints. DeBo algorithm is proposed to first solve the optimization problem to derive the decomposition policy, and then progressively calibrate decomposed models to restore performance. We demonstrate the capability to support a wide range of transformer models on heterogeneous edge devices, achieving up to 3.1× inference speedup with large transformer models. Notably, CoFormer enables the efficient inference of GPT2-XL with 1.6 billion parameters on edge devices, reducing memory requirements by 76.3%. CoFormer can also reduce energy consumption by approximately 40% while maintaining satisfactory inference performance.

Recent years have witnessed the great success of vision transformer (ViT), which has achieved state-of-the-art performance on multiple computer vision benchmarks. However, ViT models suffer from vast amounts of parameters and high computation cost, leading to difficult deployment on resource-constrained edge devices. Existing solutions mostly compress ViT models to a compact model but still cannot achieve real-time inference. To tackle this issue, we propose to explore the divisibility of transformer structure, and decompose the large ViT into multiple small models for collaborative inference at edge devices. Our objective is to achieve fast and energy-efficient collaborative inference while maintaining comparable accuracy compared with large ViTs. To this end, we first propose a collaborative inference framework termedDeViTto facilitate edge deployment by decomposing large ViTs. Subsequently, we design a decomposition-and-ensemble algorithm based on knowledge distillation, termed DEKD, to fuse multiple small decomposed models while dramatically reducing communication overheads, and handle heterogeneous models by developing a feature matching module to promote the imitations of decomposed models from the large ViT. Extensive experiments for three representative ViT backbones on four widely-used datasets demonstrate our method achieves efficient collaborative inference for ViTs and outperforms existing lightweight ViTs, striking a good trade-off between efficiency and accuracy. For example, our DeViTs improves end-to-end latency by 2.89× with only 1.65% accuracy sacrifice using CIFAR-100 compared to the large ViT, ViT-L/16, on the GPU server. DeDeiTs surpasses the recent efficient ViT, MobileViT-S, by 3.54% in accuracy on ImageNet-1 K, while running 1.72× faster and requiring 55.28% lower energy consumption on the edge device.

Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive tasks. Although early exiting is a feasible solution for accelerating inference, most works focus on convolutional neural networks (CNNs) and transformer models in natural language processing (NLP). Moreover, the direct application of early exiting methods to ViTs may result in substantial performance degradation. To tackle this challenge, we systematically investigate the efficacy of early exiting in ViTs and point out that the insufficient feature representations in shallow internal classifiers and the limited ability to capture target semantic information in deep internal classifiers restrict the performance of these methods. We then propose an early exiting framework for general ViTs termed LGViT, which incorporates heterogeneous exiting heads, namely, local perception head and global aggregation head, to achieve an efficiency-accuracy trade-off. In particular, we develop a novel two-stage training scheme, including end-to-end training and self-distillation with the backbone frozen to generate early exiting ViTs, which facilitates the fusion of global and local information extracted by the two types of heads. We conduct extensive experiments using three popular ViT backbones on three vision datasets. Results demonstrate that our LGViT can achieve competitive performance with approximately 1.8 × speed-up.

Recently, deploying deep neural network (DNN) models via collaborative inference, which splits a pre-trained model into two parts and executes them on user equipment (UE) and edge server respectively, becomes attractive. However, the large intermediate feature of DNN impedes flexible decoupling, and existing approaches either focus on the single UE scenario or simply define tasks considering the required CPU cycles, but ignore the indivisibility of a single DNN layer. In this article, we study the multi-agent collaborative inference scenario, where a single edge server coordinates the inference of multiple UEs. Our goal is to achieve fast and energy-efficient inference for all UEs. To achieve this goal, we design a lightweight autoencoder-based method to compress the large intermediate feature at first. Then we define tasks according to the inference overhead of DNNs and formulate the problem as a Markov decision process (MDP). Finally, we propose a multi-agent hybrid proximal policy optimization (MAHPPO) algorithm to solve the optimization problem with a hybrid action space. We conduct extensive experiments with different types of networks, and the results show that our method can reduce up to 56% of inference latency and save up to 72% of energy consumption.