English
Related papers

Related papers: Sparse Upcycling: Training Mixture-of-Experts from…

200 papers

Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their…

Machine Learning · Computer Science 2024-06-06 Amit Dhurandhar , Tejaswini Pedapati , Ronny Luss , Soham Dan , Aurelie Lozano , Payel Das , Georgios Kollias

Recently, sparse training methods have started to be established as a de facto approach for training and inference efficiency in artificial neural networks. Yet, this efficiency is just in theory. In practice, everyone uses a binary mask to…

Machine Learning · Computer Science 2022-07-13 Selima Curci , Decebal Constantin Mocanu , Mykola Pechenizkiyi

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xili Dai , Mingyang Li , Pengyuan Zhai , Shengbang Tong , Xingjian Gao , Shao-Lun Huang , Zhihui Zhu , Chong You , Yi Ma

Continual learning aims to enable models to adapt to new datasets without losing performance on previously learned data, often assuming that prior data is no longer available. However, in many practical scenarios, both old and new data are…

Machine Learning · Computer Science 2025-03-03 Eli Verwimp , Guy Hacohen , Tinne Tuytelaars

Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs. Examples include \textit{graph sparsification}…

Machine Learning · Computer Science 2023-02-07 Shuai Zhang , Meng Wang , Pin-Yu Chen , Sijia Liu , Songtao Lu , Miao Liu

Overparameterized neural networks generalize well but are expensive to train. Ideally, one would like to reduce their computational cost while retaining their generalization benefits. Sparse model training is a simple and promising approach…

Machine Learning · Computer Science 2022-05-12 Tri Dao , Beidi Chen , Kaizhao Liang , Jiaming Yang , Zhao Song , Atri Rudra , Christopher Ré

Linear sketching and recovery of sparse vectors with randomly constructed sparse matrices has numerous applications in several areas, including compressive sensing, data stream computing, graph sketching, and combinatorial group testing.…

Numerical Analysis · Mathematics 2014-02-07 Bubacarr Bah , Luca Baldassarre , Volkan Cevher

Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets. Generally, more accurate models on the "upstream" dataset tend to…

Computer Vision and Pattern Recognition · Computer Science 2022-04-22 Eugenia Iofinova , Alexandra Peste , Mark Kurtz , Dan Alistarh

Large language models are typically trained densely: all parameters are updated with respect to all inputs. This requires synchronization of billions of parameters across thousands of GPUs. We introduce a simple but effective method to…

Computation and Language · Computer Science 2023-03-27 Suchin Gururangan , Margaret Li , Mike Lewis , Weijia Shi , Tim Althoff , Noah A. Smith , Luke Zettlemoyer

Sparse Mixture of Expert (SMoE) models have emerged as a scalable alternative to dense models in language modeling. These models use conditionally activated feedforward subnetworks in transformer blocks, allowing for a separation between…

Machine Learning · Computer Science 2024-09-04 Soumajyoti Sarkar , Leonard Lausen , Volkan Cevher , Sheng Zha , Thomas Brox , George Karypis

Directly inspired by findings in biological vision, high-dimensional hypercolumns are feature vectors built by concatenating multi-scale activations of convolutional neural networks for a single image pixel location. Together with powerful…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Julia Dietlmeier , Vayangi Ganepola , Oluwabukola G. Adegboro , Mayug Maniparambil , Claudia Mazo , Noel E. O'Connor

Incorporating sparsity priors in learning tasks can give rise to simple, and interpretable models for complex high dimensional data. Sparse models have found widespread use in structure discovery, recovering data from corruptions, and a…

Machine Learning · Statistics 2014-03-27 Karthikeyan Natesan Ramamurthy , Aleksandr Y. Aravkin , Jayaraman J. Thiagarajan

Large Language Models (LLMs) have achieved remarkable performance on a wide range of specialized tasks, exhibiting strong problem-solving capabilities. However, training these models is prohibitively expensive, and they often lack…

Machine Learning · Computer Science 2026-04-01 Eros Fanì , Oğuzhan Ersoy

Sparsely-gated Mixture of Experts networks (MoEs) have demonstrated excellent scalability in Natural Language Processing. In Computer Vision, however, almost all performant networks are "dense", that is, every input is processed by every…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Carlos Riquelme , Joan Puigcerver , Basil Mustafa , Maxim Neumann , Rodolphe Jenatton , André Susano Pinto , Daniel Keysers , Neil Houlsby

Pre-trained large models attract widespread attention in recent years, but they face challenges in applications that require high interpretability or have limited resources, such as physical sensing, medical imaging, and bioinformatics.…

Machine Learning · Computer Science 2025-01-24 Chaoqing Tang , Huanze Zhuang , Guiyun Tian , Zhenli Zeng , Yi Ding , Wenzhong Liu , Xiang Bai

Gradient descent optimizations and backpropagation are the most common methods for training neural networks, but they are computationally expensive for real time applications, need high memory resources, and are difficult to converge for…

Machine Learning · Computer Science 2022-07-05 Seyyed Mostafa Mousavi Janbeh Sarayi , Mansour Nikkhah Bahrami

Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert…

Computation and Language · Computer Science 2025-09-15 Yixiao Zhou , Ziyu Zhao , Dongzhou Cheng , zhiliang wu , Jie Gui , Yi Yang , Fei Wu , Yu Cheng , Hehe Fan

Sparse neural networks attract increasing interest as they exhibit comparable performance to their dense counterparts while being computationally efficient. Pruning the dense neural networks is among the most widely used methods to obtain a…

Neural and Evolutionary Computing · Computer Science 2022-11-11 Zahra Atashgahi , Joost Pieterse , Shiwei Liu , Decebal Constantin Mocanu , Raymond Veldhuis , Mykola Pechenizkiy

We introduce XFT, a simple yet powerful training scheme, by simply merging upcycled Mixture-of-Experts (MoE) to unleash the performance limit of instruction-tuned code Large Language Models (LLMs). While vanilla sparse upcycling fails to…

Computation and Language · Computer Science 2024-06-10 Yifeng Ding , Jiawei Liu , Yuxiang Wei , Terry Yue Zhuo , Lingming Zhang

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