English
Related papers

Related papers: Pipe-BD: Pipelined Parallel Blockwise Distillation

200 papers

To support large-scale model training, split learning (SL) enables multiple edge devices/servers to share the intensive training workload. However, most existing works on SL focus solely on two-tier model splitting. Moreover, while some…

Networking and Internet Architecture · Computer Science 2025-09-19 Wei Wei , Zheng Lin , Tao Li , Xuanheng Li , Xianhao Chen

As the development of neural networks, more and more deep neural networks are adopted in various tasks, such as image classification. However, as the huge computational overhead, these networks could not be applied on mobile devices or…

Computer Vision and Pattern Recognition · Computer Science 2019-12-03 Yunteng Luan , Hanyu Zhao , Zhi Yang , Yafei Dai

We consider the problem of how to reduce the cost of communication that is required for the parallel training of a neural network. The state-of-the-art method, Bulk Synchronous Parallel Stochastic Gradient Descent (BSP-SGD), requires many…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-04-18 Linnan Wang , Wei Wu , George Bosilca , Richard Vuduc , Zenglin Xu

Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fall short of the state-of-the-art MCMC approach, Parallel…

The proliferation of extensive neural network architectures, particularly deep learning models, presents a challenge in terms of resource-intensive training. GPU memory constraints have become a notable bottleneck in training such sizable…

Machine Learning · Computer Science 2025-02-07 Cevat Volkan Karadağ , Nezih Topaloğlu

The expansion of neural network sizes and the enhanced resolution of modern image sensors result in heightened memory and power demands to process modern computer vision models. In order to deploy these models in extremely…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Fang Chen , Gourav Datta , Mujahid Al Rafi , Hyeran Jeon , Meng Tang

Dataset distillation aims to compress training data while preserving training-aware knowledge, alleviating the reliance on large-scale datasets in modern model training. Dataset parameterization provides a more efficient storage structure…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Chenyang Jiang , Zhengcen Li , Hang Zhao , Qiben Shan , Shaocong Wu , Jingyong Su

Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…

Computation and Language · Computer Science 2025-04-29 Wenda Xu , Rujun Han , Zifeng Wang , Long T. Le , Dhruv Madeka , Lei Li , William Yang Wang , Rishabh Agarwal , Chen-Yu Lee , Tomas Pfister

Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two coupled challenges: the fake score must track a continuously…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Zhuguanyu Wu , Ruihao Gong , Yang Yong , Yushi Huang , Xiangyu Fan , Lei Yang , Dahua Lin , Xianglong Liu

While multi-view 3D reconstruction has shifted toward large-scale foundation models capable of inferring globally consistent geometry, their reliance on massive computational clusters for training has created a significant barrier to entry…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Brandon Leblanc , Charalambos Poullis

This paper presents "Predictive Pipelined Decoding (PPD)," an approach that speeds up greedy decoding in Large Language Models (LLMs) while maintaining the exact same output as the original decoding. Unlike conventional strategies, PPD…

Computation and Language · Computer Science 2024-07-30 Seongjun Yang , Gibbeum Lee , Jaewoong Cho , Dimitris Papailiopoulos , Kangwook Lee

Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning practitioners. Distillation is typically used to compress models…

Machine Learning · Computer Science 2022-11-03 Cody Blakeney , Jessica Zosa Forde , Jonathan Frankle , Ziliang Zong , Matthew L. Leavitt

Knowledge distillation is a method of transferring the knowledge from a complex deep neural network (DNN) to a smaller and faster DNN, while preserving its accuracy. Recent variants of knowledge distillation include teaching assistant…

Machine Learning · Computer Science 2023-04-11 Minghong Gao

Contemporary machine learning requires training large neural networks on massive datasets and thus faces the challenges of high computational demands. Dataset distillation, as a recent emerging strategy, aims to compress real-world datasets…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Peng Sun , Bei Shi , Daiwei Yu , Tao Lin

Training large AI models typically requires large-scale datasets in the machine learning process, making training and parameter-tuning process both time-consuming and costly. Some researchers address this problem by carefully synthesizing a…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Jiyuan Shen , Wenzhuo Yang , Kwok-Yan Lam

With the increased penetration and proliferation of Internet of Things (IoT) devices, there is a growing trend towards distributing the power of deep learning (DL) across edge devices rather than centralizing it in the cloud. This…

Machine Learning · Computer Science 2021-10-07 Yuhao Chen , Qianqian Yang , Shibo He , Zhiguo Shi , Jiming Chen

Backpropagation (BP) has been a successful optimization technique for deep learning models. However, its limitations, such as backward- and update-locking, and its biological implausibility, hinder the concurrent updating of layers and do…

Machine Learning · Computer Science 2023-12-22 Anzhe Cheng , Zhenkun Wang , Chenzhong Yin , Mingxi Cheng , Heng Ping , Xiongye Xiao , Shahin Nazarian , Paul Bogdan

Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the transfer of…

Computation and Language · Computer Science 2024-10-22 Yuhang Zhou , Jing Zhu , Paiheng Xu , Xiaoyu Liu , Xiyao Wang , Danai Koutra , Wei Ai , Furong Huang

Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Wenmin Li , Shunsuke Sakai , Tatsuhito Hasegawa

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Usma Niyaz , Deepti R. Bathula