English
Related papers

Related papers: Exploring the Benefit of Activation Sparsity in Pr…

200 papers

Training large transformers is slow, but recent innovations on GPU architecture give us an advantage. NVIDIA Ampere GPUs can execute a fine-grained 2:4 sparse matrix multiplication twice as fast as its dense equivalent. In the light of this…

Machine Learning · Computer Science 2024-10-29 Yuezhou Hu , Kang Zhao , Weiyu Huang , Jianfei Chen , Jun Zhu

A core component present in many successful neural network architectures, is an MLP block of two fully connected layers with a non-linear activation in between. An intriguing phenomenon observed empirically, including in transformer…

Machine Learning · Computer Science 2024-06-27 Pranjal Awasthi , Nishanth Dikkala , Pritish Kamath , Raghu Meka

Despite impressive performance, deep neural networks require significant memory and computation costs, prohibiting their application in resource-constrained scenarios. Sparse training is one of the most common techniques to reduce these…

Machine Learning · Computer Science 2023-12-06 Bowen Lei , Dongkuan Xu , Ruqi Zhang , Shuren He , Bani K. Mallick

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows…

Machine Learning · Computer Science 2025-01-31 Gonçalo Paulo , Nora Belrose

Transformers are the mainstream of NLP applications and are becoming increasingly popular in other domains such as Computer Vision. Despite the improvements in model quality, the enormous computation costs make Transformers difficult at…

Machine Learning · Computer Science 2021-10-22 Liu Liu , Zheng Qu , Zhaodong Chen , Yufei Ding , Yuan Xie

Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting factor in our ability to improve network performance. One…

Machine Learning · Computer Science 2019-12-25 Simon Alford , Ryan Robinett , Lauren Milechin , Jeremy Kepner

Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit severe accuracy degradation at high sparsity. We show that this…

Machine Learning · Computer Science 2026-05-22 Haotian Xu , Jiannan Yang , Tian Gao , Tsui-Wei Weng , Tengfei Ma

Large language models (LLMs) have made significant strides in complex tasks, yet their widespread adoption is impeded by substantial computational demands. With hundreds of billion parameters, transformer-based LLMs necessitate months of…

Machine Learning · Computer Science 2024-08-22 Pihe Hu , Shaolong Li , Longbo Huang

The success of DNN pruning has led to the development of energy-efficient inference accelerators that support pruned models with sparse weight and activation tensors. Because the memory layouts and dataflows in these architectures are…

Neural and Evolutionary Computing · Computer Science 2020-09-24 Dingqing Yang , Amin Ghasemazar , Xiaowei Ren , Maximilian Golub , Guy Lemieux , Mieszko Lis

That neural networks may be pruned to high sparsities and retain high accuracy is well established. Recent research efforts focus on pruning immediately after initialization so as to allow the computational savings afforded by sparsity to…

Machine Learning · Computer Science 2022-01-28 Ilan Price , Jared Tanner

There has been an explosion of interest in designing high-performance Transformers. While Transformers have delivered significant performance improvements, training such networks is extremely memory intensive owing to storing all…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Zizheng Pan , Peng Chen , Haoyu He , Jing Liu , Jianfei Cai , Bohan Zhuang

In recent years, Dynamic Sparse Training (DST) has emerged as an alternative to post-training pruning for generating efficient models. In principle, DST allows for a more memory efficient training process, as it maintains sparsity…

Machine Learning · Computer Science 2025-02-11 Nasib Ullah , Erik Schultheis , Mike Lasby , Yani Ioannou , Rohit Babbar

Transformer models have become state-of-the-art in decoding stimuli and behavior from neural activity, significantly advancing neuroscience research. Yet greater transparency in their decision-making processes would substantially enhance…

Quantitative Methods · Quantitative Biology 2025-06-18 Laurence Freeman , Philip Shamash , Vinam Arora , Caswell Barry , Tiago Branco , Eva Dyer

Models need appropriate inductive biases to effectively learn from small amounts of data and generalize systematically outside of the training distribution. While Transformers are highly versatile and powerful, they can still benefit from…

Computation and Language · Computer Science 2024-07-08 Matthias Lindemann , Alexander Koller , Ivan Titov

Spiking neural networks (SNNs) have manifested remarkable advantages in power consumption and event-driven property during the inference process. To take full advantage of low power consumption and improve the efficiency of these models…

Neural and Evolutionary Computing · Computer Science 2023-06-07 Jiangrong Shen , Qi Xu , Jian K. Liu , Yueming Wang , Gang Pan , Huajin Tang

Structured sparsity accelerates training and inference on modern GPUs, yet it still trails unstructured dynamic sparse training (DST) in accuracy. The shortfall stems from a loss of expressivity: whereas a dense layer can realize every…

Machine Learning · Computer Science 2025-10-17 Abhishek Tyagi , Arjun Iyer , Liam Young , William H Renninger , Christopher Kanan , Yuhao Zhu

Transformer models encounter challenges in scaling hidden dimensions efficiently, as uniformly increasing them inflates computational and memory costs while failing to emphasize the most relevant features for each token. For further…

Computation and Language · Computer Science 2024-12-17 Yilong Chen , Junyuan Shang , Zhengyu Zhang , Jiawei Sheng , Tingwen Liu , Shuohuan Wang , Yu Sun , Hua Wu , Haifeng Wang

A growing intuition in machine learning suggests a link between sparsity and interpretability. We introduce a novel self-ablation mechanism to investigate this connection ante-hoc in the context of language transformers. Our approach…

Machine Learning · Computer Science 2025-05-02 Jeremias Ferrao , Luhan Mikaelson , Keenan Pepper , Natalia Perez-Campanero Antolin

In principle, sparse neural networks should be significantly more efficient than traditional dense networks. Neurons in the brain exhibit two types of sparsity; they are sparsely interconnected and sparsely active. These two types of…

Machine Learning · Computer Science 2021-12-30 Kevin Lee Hunter , Lawrence Spracklen , Subutai Ahmad

Sparse neural systems are gaining traction for efficient continual learning due to their modularity and low interference. Architectures such as Sparse Distributed Memory Multi-Layer Perceptrons (SDMLP) construct task-specific subnetworks…

Machine Learning · Computer Science 2025-12-18 Huiyan Xue , Xuming Ran , Yaxin Li , Qi Xu , Enhui Li , Yi Xu , Qiang Zhang