English
Related papers

Related papers: A Theoretical Analysis of Recommendation Loss Func…

200 papers

We propose a novel loss function that dynamically rescales the cross entropy based on prediction difficulty regarding a sample. Deep neural network architectures in image classification tasks struggle to disambiguate visually similar…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Serim Ryou , Seong-Gyun Jeong , Pietro Perona

Self-training methods have proven to be effective in exploiting abundant unlabeled data in semi-supervised learning, particularly when labeled data is scarce. While many of these approaches rely on a cross-entropy loss function (CE), recent…

Machine Learning · Computer Science 2024-09-12 Aurelien Gauffre , Julien Horvat , Massih-Reza Amini

Cross entropy loss has served as the main objective function for classification-based tasks. Widely deployed for learning neural network classifiers, it shows both effectiveness and a probabilistic interpretation. Recently, after the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Rahaf Aljundi , Yash Patel , Milan Sulc , Daniel Olmeda , Nikolay Chumerin

Learning to Rank (LTR) algorithms are usually evaluated using Information Retrieval metrics like Normalised Discounted Cumulative Gain (NDCG) or Mean Average Precision. As these metrics rely on sorting predicted items' scores (and thus, on…

Information Retrieval · Computer Science 2021-05-25 Przemysław Pobrotyn , Radosław Białobrzeski

Item recommendation is a personalized ranking task. To this end, many recommender systems optimize models with pairwise ranking objectives, such as the Bayesian Personalized Ranking (BPR). Using matrix Factorization (MF) --- the most widely…

Information Retrieval · Computer Science 2018-08-20 Xiangnan He , Zhankui He , Xiaoyu Du , Tat-Seng Chua

Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood;…

Machine Learning · Computer Science 2026-05-29 Yuanfan Li , Xiyuan Wei , Tianbao Yang , Yiming Ying

A novel method for tackling the problem of imbalanced data in medical image segmentation is proposed in this work. In balanced cross entropy (CE) loss, which is a type of weighted CE loss, the weight assigned to each class is the in-verse…

Image and Video Processing · Electrical Eng. & Systems 2024-12-10 Seyed Mohsen Hosseini , Mahdieh Soleymani Baghshah

Medical images commonly exhibit multiple abnormalities. Predicting them requires multi-class classifiers whose training and desired reliable performance can be affected by a combination of factors, such as, dataset size, data source,…

Image and Video Processing · Electrical Eng. & Systems 2021-11-16 Sivaramakrishnan Rajaraman , Ghada Zamzmi , Sameer Antani

The triplet loss with semi-hard negatives has become the de facto choice for image-caption retrieval (ICR) methods that are optimized from scratch. Recent progress in metric learning has given rise to new loss functions that outperform the…

Computer Vision and Pattern Recognition · Computer Science 2022-02-16 Maurits Bleeker , Maarten de Rijke

InfoNCE loss is a widely used loss function for contrastive model training. It aims to estimate the mutual information between a pair of variables by discriminating between each positive pair and its associated $K$ negative pairs. It is…

Machine Learning · Computer Science 2021-05-28 Chuhan Wu , Fangzhao Wu , Yongfeng Huang

In modern recommender systems, CTR/CVR models are increasingly trained with ranking objectives to improve item ranking quality. While this shift aligns training more closely with serving goals, most existing methods rely on in-batch…

Information Retrieval · Computer Science 2025-06-17 YaChen Yan , Liubo Li , Ravi Choudhary

The Expected Calibration Error (ece), the dominant calibration metric in machine learning, compares predicted probabilities against empirical frequencies of binary outcomes. This is appropriate when labels are binary events. However, many…

Machine Learning · Computer Science 2026-03-17 Michael Leznik

Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, such as sample mining or pair weighting. The standard…

Machine Learning · Computer Science 2021-11-29 Malik Boudiaf , Jérôme Rony , Imtiaz Masud Ziko , Eric Granger , Marco Pedersoli , Pablo Piantanida , Ismail Ben Ayed

Recommending cold-start items is a long-standing and fundamental challenge in recommender systems. Without any historical interaction on cold-start items, CF scheme fails to use collaborative signals to infer user preference on these items.…

Information Retrieval · Computer Science 2021-07-16 Yinwei Wei , Xiang Wang , Qi Li , Liqiang Nie , Yan Li , Xuanping Li , Tat-Seng Chua

Parameter ensembles or sets of point estimates constitute one of the cornerstones of modern statistical practice. This is especially the case in Bayesian hierarchical models, where different decision-theoretic frameworks can be deployed to…

Methodology · Statistics 2011-06-10 Cedric E. Ginestet , Nicky G. Best , Sylvia Richardson

Modern neural network classifiers achieve remarkable performance across a variety of tasks; however, they frequently exhibit overconfidence in their predictions due to the cross-entropy loss. Inspired by this problem, we propose the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Brendan Hogan Rappazzo , Aaron Ferber , Carla Gomes

Embedding-based retrieval (EBR) methods are widely used in modern recommender systems thanks to its simplicity and effectiveness. However, along the journey of deploying and iterating on EBR in production, we still identify some fundamental…

Information Retrieval · Computer Science 2023-02-07 Yuan Zhang , Xue Dong , Weijie Ding , Biao Li , Peng Jiang , Kun Gai

The choice of negative examples is important in noise contrastive estimation. Recent works find that hard negatives -- highest-scoring incorrect examples under the model -- are effective in practice, but they are used without a formal…

Computation and Language · Computer Science 2021-04-14 Wenzheng Zhang , Karl Stratos

Vast quantities of person-generated health data (wearables) are collected but the process of annotating to feed to machine learning models is impractical. This paper discusses ways in which self-supervised approaches that use contrastive…

Machine Learning · Computer Science 2021-11-16 Kevalee Shah , Dimitris Spathis , Chi Ian Tang , Cecilia Mascolo

Recommender system (RS) aims to capture personalized preferences from massive user behaviors, making them pivotal in the era of information explosion. However, the presence of ``information cocoons'', interaction sparsity, cold-start…

Information Retrieval · Computer Science 2025-07-28 Haokai Ma , Ruobing Xie , Lei Meng , Fuli Feng , Xiaoyu Du , Xingwu Sun , Zhanhui Kang , Xiangxu Meng
‹ Prev 1 4 5 6 7 8 10 Next ›