Related papers: Multi-Margin Cosine Loss: Proposal and Application…

Contrastive learning is a major studied topic in metric learning. However, sampling effective contrastive pairs remains a challenge due to factors such as limited batch size, imbalanced data distribution, and the risk of overfitting. In…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

Learning-based multi-view stereo (MVS) methods have made impressive progress and surpassed traditional methods in recent years. However, their accuracy and completeness are still struggling. In this paper, we propose a new method to enhance…

Rating is a typical user explicit feedback that visually reflects how much a user likes a related item. The (rating) matrix completion is essentially a rating prediction process, which is also a significant problem in recommender systems.…

A well-informed recommendation framework could not only help users identify their interested items, but also benefit the revenue of various online platforms (e.g., e-commerce, social media). Traditional recommendation models usually assume…

Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of models on datasets collected from different domains. Conventional approaches emphasize domain-shared information extraction and domain-private information…

Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP align…

Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…

In this paper, we perform a systemic examination of the recommendation losses, including listwise (softmax), pairwise(BPR), and pointwise (mean-squared error, MSE, and Cosine Contrastive Loss, CCL) losses through the lens of contrastive…

Learning representations that generalize well to unknown downstream tasks is a central challenge in representation learning. Existing approaches such as contrastive learning, self-supervised masking, and denoising auto-encoders address this…

Advancements in technologies related to working with omics data require novel computation methods to fully leverage information and help develop a better understanding of human diseases. This paper studies the effects of introducing graph…

In recent times, contrastive learning based loss functions have become increasingly popular for visual self-supervised representation learning owing to their state-of-the-art (SOTA) performance. Most of the modern contrastive learning…

Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. Prior literature predominantly focuses on pair-based and proxy-based methods to…

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…

In collaborative filtering, distance metric learning has been applied to matrix factorization techniques with promising results. However, matrix factorization lacks the ability of capturing collaborative information, which has been remarked…

Conversational recommender systems (CRSs) are designed to suggest the target item that the user is likely to prefer through multi-turn conversations. Recent studies stress that capturing sentiments in user conversations improves…

In this work, we aim to consider the application of contrastive learning in the scenario of the recommendation system adequately, making it more suitable for recommendation task. We propose a learning paradigm called supervised contrastive…

Deep representations have shown promising performance when transferred to downstream tasks in a black-box manner. Yet, their inherent lack of interpretability remains a significant challenge, as these features are often opaque to human…

Multimodal emotion recognition plays a key role in many domains, including mental health monitoring, educational interaction, and human-computer interaction. However, existing methods often face three major challenges: unbalanced category…

This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling. We derive a particular form of contrastive loss named Joint Contrastive Learning (JCL). JCL implicitly involves the…