Related papers: (Debiased) Contrastive Learning Loss for Recommend…

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…

Recently, self-supervised learning has attracted great attention, since it only requires unlabeled data for model training. Contrastive learning is one popular method for self-supervised learning and has achieved promising empirical…

Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification. However, unlike humans, CNNs leverage spurious features, such as background information to make decisions.…

Multi-Task Learning (MTL) plays a crucial role in real-world advertising applications such as recommender systems, aiming to achieve robust representations while minimizing resource consumption. MTL endeavors to simultaneously optimize…

This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness. We introduce supervised contrastive active learning by leveraging the contrastive…

Contrastive learning has recently seen tremendous success in self-supervised learning. So far, however, it is largely unclear why the learned representations generalize so effectively to a large variety of downstream tasks. We here prove…

Despite pre-trained language models have proven useful for learning high-quality semantic representations, these models are still vulnerable to simple perturbations. Recent works aimed to improve the robustness of pre-trained models mainly…

Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providing a way of selecting a core-set that is entirely unlabeled.…

Deep learning approaches have shown promising performance for compressed sensing-based Magnetic Resonance Imaging. While deep neural networks trained with mean squared error (MSE) loss functions can achieve high peak signal to noise ratio,…

Learning and evaluating recommender systems from logged implicit feedback is challenging due to exposure bias. While inverse propensity scoring (IPS) corrects this bias, it often suffers from high variance and instability. In this paper, we…

This paper provides a theoretical analysis of a new learning problem for recommender systems where users provide feedback by comparing pairs of items instead of rating them individually. We assume that comparisons stem from latent user and…

Speech emotion recognition is an important aspect of human-computer interaction. Prior work proposes various end-to-end models to improve the classification performance. However, most of them rely on the cross-entropy loss together with…

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…

Recommender systems and search are both indispensable in facilitating personalization and ease of browsing in online fashion platforms. However, the two tools often operate independently, failing to combine the strengths of recommender…

Recommender systems, which analyze users' preference patterns to suggest potential targets, are indispensable in today's society. Collaborative Filtering (CF) is the most popular recommendation model. Specifically, Graph Neural Network…

In implicit collaborative filtering, hard negative mining techniques are developed to accelerate and enhance the recommendation model learning. However, the inadvertent selection of false negatives remains a major concern in hard negative…

knowledge graph-based recommendation methods have achieved great success in the field of recommender systems. However, over-reliance on high-quality knowledge graphs is a bottleneck for such methods. Specifically, the long-tailed…

Average precision (AP) loss has recently shown promising performance on the dense object detection task. However,a deep understanding of how AP loss affects the detector from a pairwise ranking perspective has not yet been developed.In this…

Contrastive learning is an approach to representation learning that utilizes naturally occurring similar and dissimilar pairs of data points to find useful embeddings of data. In the context of document classification under topic modeling…

This work proposes a solution for the problem of training physics-informed networks under partial integro-differential equations. These equations require an infinite or a large number of neural evaluations to construct a single residual for…