Related papers: A Theoretical Analysis of Recommendation Loss Func…

Recommender systems guide users through vast amounts of information by suggesting items based on their predicted preferences. Collaborative filtering-based deep learning techniques have regained popularity due to their straightforward…

Noise-contrastive estimation (NCE) is a popular method for estimating unnormalised probabilistic models, such as energy-based models, which are effective for modelling complex data distributions. Unlike classical maximum likelihood (ML)…

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the…

In many contexts, there is interest in selecting the most important variables from a very large collection, commonly referred to as support recovery or variable, feature or subset selection. There is an enormous literature proposing a rich…

Instance discriminative self-supervised representation learning has been attracted attention thanks to its unsupervised nature and informative feature representation for downstream tasks. In practice, it commonly uses a larger number of…

Cross Entropy (CE) has an important role in machine learning and, in particular, in neural networks. It is commonly used in neural networks as the cost between the known distribution of the label and the Softmax/Sigmoid output. In this…

Recent work in recommender systems has emphasized the importance of fairness, with a particular interest in bias and transparency, in addition to predictive accuracy. In this paper, we focus on the state of the art pairwise ranking model,…

The learn-to-compare paradigm of contrastive representation learning (CRL), which compares positive samples with negative ones for representation learning, has achieved great success in a wide range of domains, including natural language…

Negative sampling has been heavily used to train recommender models on large-scale data, wherein sampling hard examples usually not only accelerates the convergence but also improves the model accuracy. Nevertheless, the reasons for the…

Recent advancements in learning algorithms have demonstrated that the sharpness of the loss surface is an effective measure for improving the generalization gap. Building upon this concept, Sharpness-Aware Minimization (SAM) was proposed to…

In many medical imaging and classical computer vision tasks, the Dice score and Jaccard index are used to evaluate the segmentation performance. Despite the existence and great empirical success of metric-sensitive losses, i.e. relaxations…

Recommender Systems (RS) often suffer from popularity bias, where a small set of popular items dominate the recommendation results due to their high interaction rates, leaving many less popular items overlooked. This phenomenon…

Alignment and uniformity are fundamental principles within the domain of contrastive learning. In recommender systems, prior work has established that optimizing the Bayesian Personalized Ranking (BPR) loss contributes to the objectives of…

Sequential Recommender Systems (SRSs) are a popular type of recommender system that learns from a user's history to predict the next item they are likely to interact with. However, user interactions can be affected by noise stemming from…

Recently, an alternative measure of uncertainty called cumulative residual extropy (CREX) was proposed by Jahanshahi et al. (2019). In this paper, we consider uncertainty measures of minimum ranked set sampling procedure with unequal…

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

We propose a general model-agnostic Contrastive learning framework with Counterfactual Samples Synthesizing (CCSS) for modeling the monotonicity between the neural network output and numerical features which is critical for interpretability…

We employ the Bayesian improved cross entropy (BiCE) method for rare event estimation in static networks and choose the categorical mixture as the parametric family to capture the dependence among network components. At each iteration of…

As language models grow ever larger, so do their vocabularies. This has shifted the memory footprint of LLMs during training disproportionately to one single layer: the cross-entropy in the loss computation. Cross-entropy builds up a logit…

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…