English
Related papers

Related papers: Consistency Training of Multi-exit Architectures f…

200 papers

Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-18 Xuting Liu , Daniel Alexander , Siva Kesava Reddy Kakarla , Behnaz Arzani , Vincent Liu

Automatic speech recognition models require large amounts of speech recordings for training. However, the collection of such data often is cumbersome and leads to privacy concerns. Federated learning has been widely used as an effective…

Computation and Language · Computer Science 2024-05-28 Mohamed Nabih Ali , Alessio Brutti , Daniele Falavigna

Dropout has been proven to be an effective algorithm for training robust deep networks because of its ability to prevent overfitting by avoiding the co-adaptation of feature detectors. Current explanations of dropout include bagging, naive…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Xu Shen , Xinmei Tian , Tongliang Liu , Fang Xu , Dacheng Tao

Parameter-efficient transfer learning (PETL) has shown great potential in adapting a vision transformer (ViT) pre-trained on large-scale datasets to various downstream tasks. Existing studies primarily focus on minimizing the number of…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Zheng Liu , Jinchao Zhu , Nannan Li , Gao Huang

This work aims to enable persistent, event-driven sensing and decision capabilities for energy-harvesting (EH)-powered devices by deploying lightweight DNNs onto EH-powered devices. However, harvested energy is usually weak and…

Machine Learning · Computer Science 2020-07-24 Yawen Wu , Zhepeng Wang , Zhenge Jia , Yiyu Shi , Jingtong Hu

Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural networks, has been widely studied recently. A typical EDNN has multiple prediction heads at different layers of the network backbone. During inference, the model…

Machine Learning · Computer Science 2022-12-01 Haichao Yu , Haoxiang Li , Gang Hua , Gao Huang , Humphrey Shi

Large reasoning models achieve strong performance on complex tasks by generating extended chains of thought, but they often "overthink": continuing to reason long after they have enough information to answer correctly. This wastes…

Computation and Language · Computer Science 2025-12-08 Ömer Faruk Akgül , Yusuf Hakan Kalaycı , Rajgopal Kannan , Willie Neiswanger , Viktor Prasanna

While multi-exit neural networks are regarded as a promising solution for making efficient inference via early exits, combating adversarial attacks remains a challenging problem. In multi-exit networks, due to the high dependency among…

Machine Learning · Computer Science 2023-11-02 Seokil Ham , Jungwuk Park , Dong-Jun Han , Jaekyun Moon

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes…

Machine Learning · Computer Science 2017-09-20 Tolga Bolukbasi , Joseph Wang , Ofer Dekel , Venkatesh Saligrama

In Large Language Model (LLM) inference, early-exit refers to stopping computation at an intermediate layer once the prediction is sufficiently confident, thereby reducing latency and cost. However, recent LLMs adopt improved pretraining…

Computation and Language · Computer Science 2026-03-26 Rui Wei , Rui Du , Hanfei Yu , Devesh Tiwari , Jian Li , Zhaozhuo Xu , Hao Wang

In this paper, we consider the use of deep neural networks in the context of Multiple-Input-Multiple-Output (MIMO) detection. We give a brief introduction to deep learning and propose a modern neural network architecture suitable for this…

Machine Learning · Statistics 2017-06-06 Neev Samuel , Tzvi Diskin , Ami Wiesel

Early-exit neural networks reduce inference cost by enabling confident predictions at intermediate layers. However, joint training often leads to gradient interference, with deeper classifiers dominating optimization. We propose…

Machine Learning · Computer Science 2026-01-12 Saad Mokssit , Ouassim Karrakchou , Alejandro Mousist , Mounir Ghogho

The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former's capabilities and battery lives. In a…

Information Theory · Computer Science 2023-01-02 Zhiyan Liu , Qiao Lan , Kaibin Huang

Deep Ensembles are a simple, reliable, and effective method of improving both the predictive performance and uncertainty estimates of deep learning approaches. However, they are widely criticised as being computationally expensive, due to…

Machine Learning · Computer Science 2023-10-10 Guoxuan Xia , Christos-Savvas Bouganis

Scaling machine learning models significantly improves their performance. However, such gains come at the cost of inference being slow and resource-intensive. Early-exit neural networks (EENNs) offer a promising solution: they accelerate…

Distributed DNN inference is becoming increasingly important as the demand for intelligent services at the network edge grows. By leveraging the power of distributed computing, edge devices can perform complicated and resource-hungry…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-25 Xian Peng , Xin Wu , Lianming Xu , Li Wang , Aiguo Fei

This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation. Our method…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Hojung Lee , Jong-Seok Lee

As a simple technique to accelerate inference of large-scale pre-trained models, early exiting has gained much attention in the NLP community. It allows samples to exit early at internal classifiers without passing through the entire model.…

Computation and Language · Computer Science 2021-05-31 Tianxiang Sun , Yunhua Zhou , Xiangyang Liu , Xinyu Zhang , Hao Jiang , Zhao Cao , Xuanjing Huang , Xipeng Qiu

Deep Learning has revolutionized machine learning and artificial intelligence, achieving superhuman performance in several standard benchmarks. It is well-known that deep learning models are inefficient to train; they learn by processing…

Machine Learning · Computer Science 2021-12-03 Fartash Faghri

Large pretrained models, coupled with fine-tuning, are slowly becoming established as the dominant architecture in machine learning. Even though these models offer impressive performance, their practical application is often limited by the…

Machine Learning · Computer Science 2024-05-13 Florence Regol , Joud Chataoui , Mark Coates