中文
相关论文

相关论文: Turning Noise into Value: Uncovering Service Prefe…

200 篇论文

Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk. Practitioners typically collect multiple labels…

机器学习 · 计算机科学 2018-05-22 Ashish Khetan , Zachary C. Lipton , Anima Anandkumar

Label noise is ubiquitous in various machine learning scenarios such as self-labeling with model predictions and erroneous data annotation. Many existing approaches are based on heuristics such as sample losses, which might not be flexible…

机器学习 · 计算机科学 2022-12-29 Zhihao Wang , Zongyu Lin , Peiqi Liu , Guidong ZHeng , Junjie Wen , Xianxin Chen , Yujun Chen , Zhilin Yang

Learning with noisy labels remains challenging because over-parameterized networks memorize corrupted supervision. Meta-learning-based sample reweighting mitigates this by using a small clean subset to guide training, yet its behavior and…

机器学习 · 计算机科学 2025-10-15 Yiming Zhang , Chester Holtz , Gal Mishne , Alex Cloninger

Audio-Visual Segmentation (AVS) aims to identify, at the pixel level, the object in a visual scene that produces a given sound. Current AVS methods rely on costly fine-grained annotations of mask-audio pairs, making them impractical for…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Swapnil Bhosale , Haosen Yang , Diptesh Kanojia , Jiangkang Deng , Xiatian Zhu

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

音频与语音处理 · 电气工程与系统科学 2020-11-06 Jihwan Bang , Heesu Kim , YoungJoon Yoo , Jung-Woo Ha

Many recommendation systems rely on point-wise models, which score items individually. However, point-wise models generating scores for a video are unable to account for other videos being recommended in a query. Due to this, diversity has…

信息检索 · 计算机科学 2023-04-18 Khushhall Chandra Mahajan , Aditya Palnitkar , Ameya Raul , Brad Schumitsch

Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…

机器学习 · 计算机科学 2025-10-30 Kuan Zhang , Chengliang Chai , Jingzhe Xu , Chi Zhang , Han Han , Ye Yuan , Guoren Wang , Lei Cao

Training and refreshing a web-scale Question Answering (QA) system for a multi-lingual commercial search engine often requires a huge amount of training examples. One principled idea is to mine implicit relevance feedback from user behavior…

信息检索 · 计算机科学 2020-06-17 Linjun Shou , Shining Bo , Feixiang Cheng , Ming Gong , Jian Pei , Daxin Jiang

Convolutional neural networks (CNN) have been extensively used for inverse problems. However, their prediction error for unseen test data is difficult to estimate a priori since the neural networks are trained using only selected data and…

计算机视觉与模式识别 · 计算机科学 2019-06-19 Eunju Cha , Jaeduck Jang , Junho Lee , Eunha Lee , Jong Chul Ye

Automatic extraction of product attributes from their textual descriptions is essential for online shopper experience. One inherent challenge of this task is the emerging nature of e-commerce products -- we see new types of products with…

计算与语言 · 计算机科学 2022-05-02 Xinyang Zhang , Chenwei Zhang , Xian Li , Xin Luna Dong , Jingbo Shang , Christos Faloutsos , Jiawei Han

Self-supervised learning is an increasingly popular approach to unsupervised learning, achieving state-of-the-art results. A prevalent approach consists in contrasting data points and noise points within a classification task: this requires…

机器学习 · 统计学 2023-01-25 Omar Chehab , Alexandre Gramfort , Aapo Hyvarinen

In non-stationary environments, learning machines usually confront the domain adaptation scenario where the data distribution does change over time. Previous domain adaptation works have achieved great success in theory and practice.…

机器学习 · 计算机科学 2020-05-06 Zhongyi Han , Xian-Jin Gui , Chaoran Cui , Yilong Yin

Active Learning (AL) has garnered significant interest across various application domains where labeling training data is costly. AL provides a framework that helps practitioners query informative samples for annotation by oracles…

机器学习 · 计算机科学 2025-12-16 Pouya Ahadi , Blair Winograd , Camille Zaug , Karunesh Arora , Lijun Wang , Kamran Paynabar

The complementary item recommender system (CIRS) recommends the complementary items for a given query item. Existing CIRS models consider the item co-purchase signal as a proxy of the complementary relationship due to the lack of…

信息检索 · 计算机科学 2022-02-14 Luyi Ma , Jianpeng Xu , Jason H. D. Cho , Evren Korpeoglu , Sushant Kumar , Kannan Achan

Facial Expression Recognition (FER) plays a crucial role in human affective analysis and has been widely applied in computer vision tasks such as human-computer interaction and psychological assessment. The 8th Affective Behavior Analysis…

计算机视觉与模式识别 · 计算机科学 2025-05-13 JunGyu Lee , Kunyoung Lee , Haesol Park , Ig-Jae Kim , Gi Pyo Nam

Learning from noisy labels is an important and long-standing problem in machine learning for real applications. One of the main research lines focuses on learning a label corrector to purify potential noisy labels. However, these methods…

机器学习 · 计算机科学 2023-12-05 Jian Chen , Ruiyi Zhang , Tong Yu , Rohan Sharma , Zhiqiang Xu , Tong Sun , Changyou Chen

In traditional (desktop) e-commerce search, a customer issues a specific query and the system returns a ranked list of products in order of relevance to the query. An increasingly popular alternative in e-commerce search is to issue a…

人机交互 · 计算机科学 2022-02-10 Abhisek Dash , Abhijnan Chakraborty , Saptarshi Ghosh , Animesh Mukherjee , Krishna P. Gummadi

Implicit feedback is central to modern recommender systems but is inherently noisy, often impairing model training and degrading user experience. At scale, such noise can mislead learning processes, reducing both recommendation accuracy and…

信息检索 · 计算机科学 2025-10-13 Ze Liu , Xianquan Wang , Shuochen Liu , Jie Ma , Huibo Xu , Yupeng Han , Kai Zhang , Jun Zhou

Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean…

机器学习 · 统计学 2022-07-13 Yingsong Huang , Bing Bai , Shengwei Zhao , Kun Bai , Fei Wang

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training…

计算机视觉与模式识别 · 计算机科学 2022-07-20 Kai Wang , Xiangyu Peng , Shuo Yang , Jianfei Yang , Zheng Zhu , Xinchao Wang , Yang You