English
Related papers

Related papers: A Static Pruning Study on Sparse Neural Retrievers

200 papers

Weight pruning is among the most popular approaches for compressing deep convolutional neural networks. Recent work suggests that in a randomly initialized deep neural network, there exist sparse subnetworks that achieve performance…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Vinay Kumar Verma , Nikhil Mehta , Shijing Si , Ricardo Henao , Lawrence Carin

Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on tiny, embedded devices such as low-power micro-controller…

Machine Learning · Computer Science 2023-08-21 Marcus Rüb , Daniel Maier , Daniel Mueller-Gritschneder , Axel Sikora

Sparsification is an efficient approach to accelerate CNN inference, but it is challenging to take advantage of sparsity in training procedure because the involved gradients are dynamically changed. Actually, an important observation shows…

Machine Learning · Computer Science 2020-07-21 Xucheng Ye , Pengcheng Dai , Junyu Luo , Xin Guo , Yingjie Qi , Jianlei Yang , Yiran Chen

A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows. The neural IR community made great advancements in training effective dual-encoder…

Information Retrieval · Computer Science 2021-05-27 Sebastian Hofstätter , Sheng-Chieh Lin , Jheng-Hong Yang , Jimmy Lin , Allan Hanbury

Ranking has always been one of the top concerns in information retrieval researches. For decades, the lexical matching signal has dominated the ad-hoc retrieval process, but solely using this signal in retrieval may cause the vocabulary…

Information Retrieval · Computer Science 2021-04-19 Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Jiafeng Guo , Min Zhang , Shaoping Ma

Spiking Neural Networks (SNNs) may offer an energy-efficient alternative for implementing deep learning applications. In recent years, there have been several proposals focused on supervised (conversion, spike-based gradient descent) and…

Computer Vision and Pattern Recognition · Computer Science 2019-10-31 Priyadarshini Panda , Aparna Aketi , Kaushik Roy

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational similarity between the…

Machine Learning · Computer Science 2021-10-01 James O' Neill , Sourav Dutta , Haytham Assem

IR models using a pretrained language model significantly outperform lexical approaches like BM25. In particular, SPLADE, which encodes texts to sparse vectors, is an effective model for practical use because it shows robustness to…

Computation and Language · Computer Science 2022-11-11 Hiroki Iida , Naoaki Okazaki

While dense retrieval models have become the standard for state-of-the-art information retrieval, their deployment is often constrained by high memory requirements and reliance on GPU accelerators for vector similarity search. Learned…

Information Retrieval · Computer Science 2026-01-06 Zhichao Xu , Shengyao Zhuang , Crystina Zhang , Xueguang Ma , Yijun Tian , Maitrey Mehta , Jimmy Lin , Vivek Srikumar

Neural information retrieval systems typically use a cascading pipeline, in which a first-stage model retrieves a candidate set of documents and one or more subsequent stages re-rank this set using contextualized language models such as…

Information Retrieval · Computer Science 2021-04-27 Antonio Mallia , Omar Khattab , Nicola Tonellotto , Torsten Suel

Finetuning large language models inflates the costs of NLU applications and remains the bottleneck of development cycles. Recent works in computer vision use data pruning to reduce training time. Pruned data selection with static methods is…

Computation and Language · Computer Science 2023-06-07 Jean-Michel Attendu , Jean-Philippe Corbeil

Ad relevance modeling plays a critical role in online advertising systems including Microsoft Bing. To leverage powerful transformers like BERT in this low-latency setting, many existing approaches perform ad-side computations offline.…

Information Retrieval · Computer Science 2022-09-02 Li Lyna Zhang , Youkow Homma , Yujing Wang , Min Wu , Mao Yang , Ruofei Zhang , Ting Cao , Wei Shen

Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the…

Machine Learning · Computer Science 2023-09-11 Denis Kuznedelev , Eldar Kurtic , Eugenia Iofinova , Elias Frantar , Alexandra Peste , Dan Alistarh

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

Effectively scaling up deep reinforcement learning models has proven notoriously difficult due to network pathologies during training, motivating various targeted interventions such as periodic reset and architectural advances such as layer…

Machine Learning · Computer Science 2025-06-23 Guozheng Ma , Lu Li , Zilin Wang , Li Shen , Pierre-Luc Bacon , Dacheng Tao

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Machine Learning · Computer Science 2021-11-11 Xiao Zhou , Weizhong Zhang , Zonghao Chen , Shizhe Diao , Tong Zhang

Speculative decoding accelerates Large Language Model inference via a draft-then-verify paradigm, yet the output projection layer becomes a bottleneck as vocabulary sizes scale. While existing static pruning methods effectively reduce this…

Computation and Language · Computer Science 2026-05-29 Shuyu Zhang , Lingfeng Pan , Qicheng Wang , Yaqi Shi , Yueyang Tan , Ruyu Yan , Jiaqi Chen , Lixing Du , Lu Wang

Over-parameterization of deep neural networks (DNNs) has shown high prediction accuracy for many applications. Although effective, the large number of parameters hinders its popularity on resource-limited devices and has an outsize…

Machine Learning · Computer Science 2023-04-25 Shaoyi Huang , Bowen Lei , Dongkuan Xu , Hongwu Peng , Yue Sun , Mimi Xie , Caiwen Ding

Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them from being deployed to many edge and internet-of-things (IoT)…

Neural and Evolutionary Computing · Computer Science 2021-12-22 Minghai Qin , Tianyun Zhang , Fei Sun , Yen-Kuang Chen , Makan Fardad , Yanzhi Wang , Yuan Xie

Compression of convolutional neural network models has recently been dominated by pruning approaches. A class of previous works focuses solely on pruning the unimportant filters to achieve network compression. Another important direction is…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Tariq M. Khan , Syed S. Naqvi , Antonio Robles-Kelly , Erik Meijering