English
Related papers

Related papers: Sparse Growing Transformer: Training-Time Sparse D…

200 papers

Sparse learning is ubiquitous in many machine learning tasks. It aims to regularize the goodness-of-fit objective by adding a penalty term to encode structural constraints on the model parameters. In this paper, we develop a flexible sparse…

Machine Learning · Statistics 2026-02-10 Yingjie Wang , Mokhtar Z. Alaya , Salim Bouzebda , Xinsheng Liu

Graph Neural Networks (GNNs) excel in various graph learning tasks but face computational challenges when applied to large-scale graphs. A promising solution is to remove non-essential edges to reduce the computational overheads in GNN.…

Machine Learning · Computer Science 2024-02-05 Guibin Zhang , Yanwei Yue , Kun Wang , Junfeng Fang , Yongduo Sui , Kai Wang , Yuxuan Liang , Dawei Cheng , Shirui Pan , Tianlong Chen

We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations. Concretely, we introduce a meta sorting network that learns to…

Machine Learning · Computer Science 2020-02-27 Yi Tay , Dara Bahri , Liu Yang , Donald Metzler , Da-Cheng Juan

Stochastic Gradient Descent (SGD) has proven to be remarkably effective in optimizing deep neural networks that employ ever-larger numbers of parameters. Yet, improving the efficiency of large-scale optimization remains a vital and highly…

Machine Learning · Computer Science 2020-11-11 Frithjof Gressmann , Zach Eaton-Rosen , Carlo Luschi

Graph neural networks (GNNs) are emerging as a powerful technique for modeling graph structures. Due to the sparsity of real-world graph data, GNN performance is limited by extensive sparse matrix multiplication (SpMM) operations involved…

Machine Learning · Computer Science 2021-11-02 Shenghao Qiu , You Liang , Zheng Wang

We explore a key architectural aspect of deep convolutional neural networks: the pattern of internal skip connections used to aggregate outputs of earlier layers for consumption by deeper layers. Such aggregation is critical to facilitate…

Computer Vision and Pattern Recognition · Computer Science 2019-02-08 Ligeng Zhu , Ruizhi Deng , Michael Maire , Zhiwei Deng , Greg Mori , Ping Tan

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…

Machine Learning · Computer Science 2024-09-11 Minhong Zhu , Zhenhao Zhao , Weiran Cai

While sparse attention mitigates the computational bottleneck of long-context LLM training, its distributed training process exhibits extreme heterogeneity in both \textit{1)} sequence length and \textit{2)} sparsity sensitivity, leading to…

Machine Learning · Computer Science 2026-04-27 Hongtao Xu , Jianchao Tan , Yuxuan Hu , Pengju Lu , Hongyu Wang , Pingwei Sun , Yerui Sun , Yuchen Xie , Xunliang Cai , Mingzhen Li , Weile Jia

This paper introduces a high-order Markov chain task to investigate how transformers learn to integrate information from multiple past positions with varying statistical significance. We demonstrate that transformers learn this task…

Machine Learning · Computer Science 2026-02-24 Oğuz Kaan Yüksel , Rodrigo Alvarez Lucendo , Nicolas Flammarion

The majority of research in both training Artificial Neural Networks (ANNs) and modeling learning in biological brains focuses on synaptic plasticity, where learning equates to changing the strength of existing connections. However, in…

Neural and Evolutionary Computing · Computer Science 2026-03-13 James C. Knight , Johanna Senk , Thomas Nowotny

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

Machine Learning · Computer Science 2025-05-27 Dan Peng , Zhihui Fu , Zewen Ye , Zhuoran Song , Jun Wang

Dropout is a common regularisation technique in deep learning that improves generalisation. Even though it introduces sparsity and thus potential for higher throughput, it usually cannot bring speed-ups on GPUs due to its unstructured…

Machine Learning · Computer Science 2024-11-05 Andy Lo

Differentially private stochastic gradient descent (DP-SGD) is broadly considered to be the gold standard for training and fine-tuning neural networks under differential privacy (DP). With the increasing availability of high-quality…

Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…

Computation and Language · Computer Science 2022-04-22 Marcos Treviso , António Góis , Patrick Fernandes , Erick Fonseca , André F. T. Martins

Deep spiking neural networks (SNNs) have emerged as a potential alternative to traditional deep learning frameworks, due to their promise to provide increased compute efficiency on event-driven neuromorphic hardware. However, to perform…

Neural and Evolutionary Computing · Computer Science 2021-07-28 Souvik Kundu , Gourav Datta , Massoud Pedram , Peter A. Beerel

Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization). The…

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of…

Machine Learning · Computer Science 2025-11-20 Jintao Zhang , Chendong Xiang , Haofeng Huang , Jia Wei , Haocheng Xi , Jun Zhu , Jianfei Chen

Training large language models to predict beyond their training context lengths has drawn much attention in recent years, yet the principles driving such behavior of length generalization remain underexplored. We propose a new theoretical…

Machine Learning · Computer Science 2025-02-25 Noah Golowich , Samy Jelassi , David Brandfonbrener , Sham M. Kakade , Eran Malach

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost…

Machine Learning · Computer Science 2024-06-11 Weixi Song , Zuchao Li , Lefei Zhang , Hai Zhao , Bo Du

Recommender systems often rely on large embedding tables that map users and items to dense vectors of uniform size, leading to substantial memory consumption and inefficiencies. This is particularly problematic in memory-constrained…

Information Retrieval · Computer Science 2024-11-20 Yunke Qu , Liang Qu , Tong Chen , Xiangyu Zhao , Jianxin Li , Hongzhi Yin
‹ Prev 1 4 5 6 7 8 10 Next ›