English
Related papers

Related papers: SparseGPT: Massive Language Models Can Be Accurate…

200 papers

To improve federated training of neural networks, we develop FedSparsify, a sparsification strategy based on progressive weight magnitude pruning. Our method has several benefits. First, since the size of the network becomes increasingly…

Machine Learning · Computer Science 2023-05-17 Dimitris Stripelis , Umang Gupta , Greg Ver Steeg , Jose Luis Ambite

Large language models (LLMs) demonstrate strong performance as text embedding models when finetuned with supervised contrastive training. However, their large size balloons inference time and memory requirements. In this paper, we show that…

Computation and Language · Computer Science 2024-10-21 Thennal D K , Tim Fischer , Chris Biemann

Large language models (LLMs) have revolutionized natural language processing, yet their substantial model sizes often require substantial computational resources. To preserve computing resources and accelerate inference speed, it is crucial…

Computation and Language · Computer Science 2025-06-04 Yirao Zhao , Guizhen Chen , Kenji Kawaguchi , Lidong Bing , Wenxuan Zhang

Weight pruning is a powerful technique to realize model compression. We propose PCNN, a fine-grained regular 1D pruning method. A novel index format called Sparsity Pattern Mask (SPM) is presented to encode the sparsity in PCNN. Leveraging…

Machine Learning · Computer Science 2020-06-16 Zhanhong Tan , Jiebo Song , Xiaolong Ma , Sia-Huat Tan , Hongyang Chen , Yuanqing Miao , Yifu Wu , Shaokai Ye , Yanzhi Wang , Dehui Li , Kaisheng Ma

Post-training pruning is an effective approach for reducing the size and inference cost of large language models (LLMs), but existing methods often face a trade-off between pruning quality and computational efficiency. Heuristic pruning…

Computation and Language · Computer Science 2026-02-10 Peiqi Yu , Jinhao Wang , Xinyi Sui , Nam Ling , Wei Wang , Wei Jiang

Pruning large language models (LLMs) is a promising solution for reducing model sizes and computational complexity while preserving performance. Traditional layer-wise pruning methods often adopt a uniform sparsity approach across all…

Computation and Language · Computer Science 2025-05-22 Chuan Sun , Han Yu , Lizhen Cui , Xiaoxiao Li

Large Language Models (LLMs) have become pivotal in advancing the field of artificial intelligence, yet their immense sizes pose significant challenges for both fine-tuning and deployment. Current post-training pruning methods, while…

Computation and Language · Computer Science 2024-05-28 Xudong Lu , Aojun Zhou , Yuhui Xu , Renrui Zhang , Peng Gao , Hongsheng Li

Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, we tackle these costs by leveraging unstructured sparsity within an LLM's feedforward layers, the…

Machine Learning · Computer Science 2026-05-11 Edoardo Cetin , Stefano Peluchetti , Emilio Castillo , Akira Naruse , Mana Murakami , Llion Jones

Weight pruning is an effective technique to reduce the model size and inference time for deep neural networks in real-world deployments. However, since magnitudes and relative importance of weights are very different for different layers of…

Machine Learning · Computer Science 2021-05-05 Xiao Zhou , Weizhong Zhang , Hang Xu , Tong Zhang

The energy consumption of large-scale ML models is dominated by data movement, shuffling billions of parameters across memory hierarchies and data centers. Sparsification offers a principled way to mitigate these costs by pruning redundant…

Modern Convolutional Neural Networks (CNNs) are complex, encompassing millions of parameters. Their deployment exerts computational, storage and energy demands, particularly on embedded platforms. Existing approaches to prune or sparsify…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Amir H. Ashouri , Tarek S. Abdelrahman , Alwyn Dos Remedios

Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accelerators such as TPU. The structure of sparsity, i.e., the…

Machine Learning · Computer Science 2017-06-06 Huizi Mao , Song Han , Jeff Pool , Wenshuo Li , Xingyu Liu , Yu Wang , William J. Dally

The state of the art of many learning tasks, e.g., image classification, is advanced by collecting larger datasets and then training larger models on them. As the outcome, the increasing computational cost is becoming unaffordable. In this…

Machine Learning · Computer Science 2024-06-17 Muyang He , Shuo Yang , Tiejun Huang , Bo Zhao

Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse…

Neural and Evolutionary Computing · Computer Science 2019-06-28 Shiwei Liu , Decebal Constantin Mocanu , Mykola Pechenizkiy

Pruning aims to accelerate and compress models by removing redundant parameters, identified by specifically designed importance scores which are usually imperfect. This removal is irreversible, often leading to subpar performance in pruned…

Machine Learning · Computer Science 2025-02-07 Xinglong Sun , Maying Shen , Hongxu Yin , Lei Mao , Pavlo Molchanov , Jose M. Alvarez

It is widely acknowledged that large and sparse models have higher accuracy than small and dense models under the same model size constraints. This motivates us to train a large model and then remove its redundant neurons or weights by…

Computer Vision and Pattern Recognition · Computer Science 2024-01-12 Jianwei Li , Weizhi Gao , Qi Lei , Dongkuan Xu

Text-to-speech (TTS) models have achieved remarkable naturalness in recent years, yet like most deep neural models, they have more parameters than necessary. Sparse TTS models can improve on dense models via pruning and extra retraining, or…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-04 Perry Lam , Huayun Zhang , Nancy F. Chen , Berrak Sisman , Dorien Herremans

To overcome the overparameterized problem in Pre-trained Language Models (PLMs), pruning is widely used as a simple and straightforward compression method by directly removing unimportant weights. Previous first-order methods successfully…

Computation and Language · Computer Science 2023-05-18 Ting Jiang , Deqing Wang , Fuzhen Zhuang , Ruobing Xie , Feng Xia

Sparsity in the structure of Neural Networks can lead to less energy consumption, less memory usage, faster computation times on convenient hardware, and automated machine learning. If sparsity gives rise to certain kinds of structure, it…

Machine Learning · Computer Science 2021-07-28 Julian Stier , Harshil Darji , Michael Granitzer

Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection layer when performing speculative decoding. Current methods for vocabulary pruning depend…

Computation and Language · Computer Science 2026-05-27 Zhiyang Chen , Daliang Xu , Yinyuan Zhang , Chenghua Wang , Mengwei Xu , Yun Ma