English
Related papers

Related papers: Utilizing dynamic sparsity on pretrained DETR

200 papers

Our community has greatly improved the efficiency of deep learning applications, including by exploiting sparsity in inputs. Most of that work, though, is for inference, where weight sparsity is known statically, and/or for specialized…

Machine Learning · Computer Science 2020-12-04 Zhangxiaowen Gong , Houxiang Ji , Christopher Fletcher , Christopher Hughes , Josep Torrellas

We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference. The great success of DNNs motivates the pursuing of…

Machine Learning · Computer Science 2019-05-08 Liu Liu , Lei Deng , Xing Hu , Maohua Zhu , Guoqi Li , Yufei Ding , Yuan Xie

Learned sparse retrieval (LSR) is a family of neural methods that encode queries and documents into sparse lexical vectors that can be indexed and retrieved efficiently with an inverted index. We explore the application of LSR to the…

Information Retrieval · Computer Science 2024-02-28 Thong Nguyen , Mariya Hendriksen , Andrew Yates , Maarten de Rijke

Deploying large language models (LLMs) on end-user devices is gaining importance due to benefits in responsiveness, privacy, and operational cost. Yet the limited memory and compute capability of mobile and desktop GPUs make efficient…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-07 Rongxiang Wang , Kangyuan Shu , Felix Xiaozhu Lin

Leveraging sparsity is crucial for optimizing large language model inference. however, modern LLMs employing SiLU as their activation function exhibit minimal activation sparsity. Recent research has proposed replacing SiLU with ReLU to…

Performance · Computer Science 2025-01-27 Jiho Shin , Hoeseok Yang , Youngmin Yi

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

To reduce the long training time of large deep neural network (DNN) models, distributed synchronous stochastic gradient descent (S-SGD) is commonly used on a cluster of workers. However, the speedup brought by multiple workers is limited by…

Machine Learning · Computer Science 2020-03-03 Shaohuai Shi , Zhenheng Tang , Qiang Wang , Kaiyong Zhao , Xiaowen Chu

This paper studies the curious phenomenon for machine learning models with Transformer architectures that their activation maps are sparse. By activation map we refer to the intermediate output of the multi-layer perceptrons (MLPs) after a…

Plasticity loss, a diminishing capacity to adapt as training progresses, is a critical challenge in deep reinforcement learning. We examine this issue in multi-task reinforcement learning (MTRL), where higher representational flexibility is…

Machine Learning · Computer Science 2025-08-12 Aleksandar Todorov , Juan Cardenas-Cartagena , Rafael F. Cunha , Marco Zullich , Matthia Sabatelli

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically…

Machine Learning · Computer Science 2020-12-29 Gonçalo M. Correia , Vlad Niculae , Wilker Aziz , André F. T. Martins

Transformers have been essential to pretraining success in NLP. While other architectures have been used, downstream accuracy is either significantly worse, or requires attention layers to match standard benchmarks such as GLUE. This work…

Computation and Language · Computer Science 2023-05-10 Junxiong Wang , Jing Nathan Yan , Albert Gu , Alexander M. Rush

Machine/deep-learning (ML/DL) based techniques are emerging as a driving force behind many cutting-edge technologies, achieving high accuracy on computer vision workloads such as image classification and object detection. However, training…

Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited. In this work, we provide evidence that disentangled representations coupled with sparse…

Efficient time series forecasting has become critical for real-world applications, particularly with deep neural networks (DNNs). Efficiency in DNNs can be achieved through sparse connectivity and reducing the model size. However, finding…

Machine Learning · Computer Science 2024-06-13 Zahra Atashgahi , Mykola Pechenizkiy , Raymond Veldhuis , Decebal Constantin Mocanu

We propose a novel adaptive empirical Bayesian method for sparse deep learning, where the sparsity is ensured via a class of self-adaptive spike-and-slab priors. The proposed method works by alternatively sampling from an adaptive…

Machine Learning · Statistics 2020-04-15 Wei Deng , Xiao Zhang , Faming Liang , Guang Lin

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…

Machine Learning · Computer Science 2026-05-19 Kean Shi , Liang Chen , Haozhe Zhao , Baobao Chang

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

Machine Learning · Computer Science 2026-02-11 Jonathan Svirsky , Yehonathan Refael , Ofir Lindenbaum

Stability arguments are often used to prevent learning algorithms from having ever increasing activity and weights that hinder generalization. However, stability conditions can clash with the sparsity required to augment the energy…

Neural and Evolutionary Computing · Computer Science 2024-01-08 Luca Herranz-Celotti , Jean Rouat

Deep neural networks often suffer from poor generalization caused by complex and non-convex loss landscapes. One of the popular solutions is Sharpness-Aware Minimization (SAM), which smooths the loss landscape via minimizing the maximized…

Machine Learning · Computer Science 2022-10-25 Peng Mi , Li Shen , Tianhe Ren , Yiyi Zhou , Xiaoshuai Sun , Rongrong Ji , Dacheng Tao

Sparse Neural Networks (SNNs) can potentially demonstrate similar performance to their dense counterparts while saving significant energy and memory at inference. However, the accuracy drop incurred by SNNs, especially at high pruning…

Machine Learning · Computer Science 2023-06-06 Mohammad Loni , Aditya Mohan , Mehdi Asadi , Marius Lindauer