English
Related papers

Related papers: Navigating Extremes: Dynamic Sparsity in Large Out…

200 papers

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

In the realm of deep learning-based recommendation systems, the increasing computational demands, driven by the growing number of users and items, pose a significant challenge to practical deployment. This challenge is primarily twofold:…

Information Retrieval · Computer Science 2024-02-06 Shuyao Wang , Yongduo Sui , Jiancan Wu , Zhi Zheng , Hui Xiong

Recent studies demonstrate that deep networks, even robustified by the state-of-the-art adversarial training (AT), still suffer from large robust generalization gaps, in addition to the much more expensive training costs than standard…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Tianlong Chen , Zhenyu Zhang , Pengjun Wang , Santosh Balachandra , Haoyu Ma , Zehao Wang , Zhangyang Wang

Training a sparse neural network from scratch requires optimizing connections at the same time as the weights themselves. Typically, the weights are redistributed after a predefined number of weight updates, removing a fraction of the…

Machine Learning · Computer Science 2022-11-04 Mathias Parger , Alexander Ertl , Paul Eibensteiner , Joerg H. Mueller , Martin Winter , Markus Steinberger

The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community has proposed sparse attention to mitigate this issue.…

Artificial Intelligence · Computer Science 2025-11-18 Jingze Shi , Yifan Wu , Yiran Peng , Bingheng Wu , Liangdong Wang , Guang Liu , Yuyu Luo

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

Continual learning on edge devices poses unique challenges due to stringent resource constraints. This paper introduces a novel method that leverages stochastic competition principles to promote sparsity, significantly reducing deep network…

Machine Learning · Computer Science 2024-07-16 Theodoros Christophides , Kyriakos Tolias , Sotirios Chatzis

Deep neural networks (DNNs) have emerged as key enablers of machine learning. Applying larger DNNs to more diverse applications is an important challenge. The computations performed during DNN training and inference are dominated by…

Machine Learning · Computer Science 2018-12-17 Jeremy Kepner , Vijay Gadepally , Hayden Jananthan , Lauren Milechin , Sid Samsi

One key challenge of exemplar-guided image generation lies in establishing fine-grained correspondences between input and guided images. Prior approaches, despite the promising results, have relied on either estimating dense attention to…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Songhua Liu , Jingwen Ye , Sucheng Ren , Xinchao Wang

Learning with noisy labels is an important and challenging task for training accurate deep neural networks. Some commonly-used loss functions, such as Cross Entropy (CE), suffer from severe overfitting to noisy labels. Robust loss functions…

Machine Learning · Computer Science 2021-08-03 Xiong Zhou , Xianming Liu , Chenyang Wang , Deming Zhai , Junjun Jiang , Xiangyang Ji

Real-world applications often require learning continuously from a stream of data under ever-changing conditions. When trying to learn from such non-stationary data, deep neural networks (DNNs) undergo catastrophic forgetting of previously…

Computer Vision and Pattern Recognition · Computer Science 2023-01-03 Arnav Varma , Elahe Arani , Bahram Zonooz

While larger neural models are pushing the boundaries of what deep learning can do, often more weights are needed to train models rather than to run inference for tasks. This paper seeks to understand this behavior using search spaces --…

Machine Learning · Computer Science 2021-05-28 Darko Stosic , Dusan Stosic

Deep Learning (DL) has achieved unprecedented success in various application domains. Meanwhile, model pruning has emerged as a viable solution to reduce the footprint of DL models in mobile applications, without compromising their…

Hardware Architecture · Computer Science 2024-01-17 Christodoulos Peltekis , Vasileios Titopoulos , Chrysostomos Nicopoulos , Giorgos Dimitrakopoulos

Sparsification-based pruning has been an important category in model compression. Existing methods commonly set sparsity-inducing penalty terms to suppress the importance of dropped weights, which is regarded as the suppressed…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Shengji Tang , Weihao Lin , Hancheng Ye , Peng Ye , Chong Yu , Baopu Li , Tao Chen

Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration…

Machine Learning · Computer Science 2022-07-07 Ryuichi Ito , Seng Pei Liew , Tsubasa Takahashi , Yuya Sasaki , Makoto Onizuka

Generative graph models struggle to scale due to the need to predict the existence or type of edges between all node pairs. To address the resulting quadratic complexity, existing scalable models often impose restrictive assumptions such as…

Machine Learning · Computer Science 2024-05-24 Yiming Qin , Clement Vignac , Pascal Frossard

Sparse coding strategies have been lauded for their parsimonious representations of data that leverage low dimensional structure. However, inference of these codes typically relies on an optimization procedure with poor computational…

Machine Learning · Computer Science 2022-09-02 Kion Fallah , Christopher J. Rozell

The Transformer has been an indispensable staple in deep learning. However, for real-life applications, it is very challenging to deploy efficient Transformers due to immense parameters and operations of models. To relieve this burden,…

Hardware Architecture · Computer Science 2022-11-01 Chao Fang , Aojun Zhou , Zhongfeng Wang

Neural networks augmented with external memory have the ability to learn algorithmic solutions to complex tasks. These models appear promising for applications such as language modeling and machine translation. However, they scale poorly in…

Machine Learning · Computer Science 2016-10-31 Jack W Rae , Jonathan J Hunt , Tim Harley , Ivo Danihelka , Andrew Senior , Greg Wayne , Alex Graves , Timothy P Lillicrap

The compression of deep neural networks (DNNs) to reduce inference cost becomes increasingly important to meet realistic deployment requirements of various applications. There have been a significant amount of work regarding network…

Machine Learning · Computer Science 2020-11-12 Tianyi Chen , Bo Ji , Yixin Shi , Tianyu Ding , Biyi Fang , Sheng Yi , Xiao Tu