中文
相关论文

相关论文: To Compress or Not to Compress- Self-Supervised Le…

200 篇论文

In recent years, neural architecture-based recommender systems have achieved tremendous success, but they still fall short of expectation when dealing with highly sparse data. Self-supervised learning (SSL), as an emerging technique for…

信息检索 · 计算机科学 2023-06-05 Junliang Yu , Hongzhi Yin , Xin Xia , Tong Chen , Jundong Li , Zi Huang

While supervised learning models have shown remarkable performance in various natural language processing (NLP) tasks, their success heavily relies on the availability of large-scale labeled datasets, which can be costly and time-consuming…

计算与语言 · 计算机科学 2024-06-04 Wrick Talukdar , Anjanava Biswas

The information noise-contrastive estimation (InfoNCE) loss function provides the basis of many self-supervised deep learning methods due to its strong empirical results and theoretic motivation. Previous work suggests a supervised…

计算机视觉与模式识别 · 计算机科学 2024-11-11 Patrick Feeney , Michael C. Hughes

Semi-supervised learning, which has emerged from the beginning of this century, is a new type of learning method between traditional supervised learning and unsupervised learning. The main idea of semi-supervised learning is to introduce…

机器学习 · 计算机科学 2019-05-29 Enmei Tu , Jie Yang

Self-supervised learning has significantly improved the performance of many NLP tasks. However, how can self-supervised learning discover useful representations, and why is it better than traditional approaches such as probabilistic models…

计算与语言 · 计算机科学 2023-03-01 Zeping Luo , Shiyou Wu , Cindy Weng , Mo Zhou , Rong Ge

In the realm of neural network models, the perpetual challenge remains in retaining task-relevant information while effectively discarding redundant data during propagation. In this paper, we introduce IB-AdCSCNet, a deep learning model…

计算机视觉与模式识别 · 计算机科学 2024-05-24 He Zou , Meng'en Qin , Yu Song , Xiaohui Yang

Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…

机器学习 · 计算机科学 2021-08-18 Hilal AlQuabeh , Ameera Bawazeer , Abdulateef Alhashmi

By extracting task-relevant information while maximally compressing the input, the information bottleneck (IB) principle has provided a guideline for learning effective and robust representations of the target inference. However, extending…

信息论 · 计算机科学 2025-01-22 Yuhan Wang , Youlong Wu , Shuai Ma , Ying-Jun Angela Zhang

Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of…

机器学习 · 计算机科学 2023-11-06 Banghua Zhu , Mingyu Ding , Philip Jacobson , Ming Wu , Wei Zhan , Michael Jordan , Jiantao Jiao

While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…

计算机视觉与模式识别 · 计算机科学 2018-09-03 Qingnan Fan , Jiaolong Yang , Gang Hua , Baoquan Chen , David Wipf

In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than…

人工智能 · 计算机科学 2016-09-20 Russell Stewart , Stefano Ermon

Deep supervised learning has achieved great success in the last decade. However, its deficiencies of dependence on manual labels and vulnerability to attacks have driven people to explore a better solution. As an alternative,…

机器学习 · 计算机科学 2021-06-28 Xiao Liu , Fanjin Zhang , Zhenyu Hou , Zhaoyu Wang , Li Mian , Jing Zhang , Jie Tang

In this paper we consider the problem of semi-supervised learning with deep Convolutional Neural Networks (ConvNets). Semi-supervised learning is motivated on the observation that unlabeled data is cheap and can be used to improve the…

计算机视觉与模式识别 · 计算机科学 2016-06-13 Mehdi Sajjadi , Mehran Javanmardi , Tolga Tasdizen

This paper presents a novel information-theoretic perspective on generalization in machine learning by framing the learning problem within the context of lossy compression and applying finite blocklength analysis. In our approach, the…

机器学习 · 计算机科学 2026-02-05 Kosuke Sugiyama , Masato Uchida

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

机器学习 · 计算机科学 2018-12-05 Elad Hoffer , Itay Hubara , Nir Ailon

Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noisy label learning.…

机器学习 · 计算机科学 2023-06-08 Jingyi Cui , Weiran Huang , Yifei Wang , Yisen Wang

Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of…

机器学习 · 计算机科学 2018-12-05 Elad Hoffer , Nir Ailon

Modern advancements in large-scale machine learning would be impossible without the paradigm of data-parallel distributed computing. Since distributed computing with large-scale models imparts excessive pressure on communication channels,…

机器学习 · 计算机科学 2024-06-05 Egor Shulgin , Peter Richtárik

Representation learning with small labeled data have emerged in many problems, since the success of deep neural networks often relies on the availability of a huge amount of labeled data that is expensive to collect. To address it, many…

计算机视觉与模式识别 · 计算机科学 2021-01-05 Guo-Jun Qi , Jiebo Luo

The information bottleneck principle is an elegant and useful approach to representation learning. In this paper, we investigate the problem of representation learning in the context of reinforcement learning using the information…

机器学习 · 计算机科学 2019-11-14 Pei Yingjun , Hou Xinwen