Related papers: Advancing Loss Functions in Recommender Systems: A…
Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendation research. Among various losses, we find Softmax loss (SL)…
Softmax Loss (SL) is widely applied in recommender systems (RS) and has demonstrated effectiveness. This work analyzes SL from a pairwise perspective, revealing two significant limitations: 1) the relationship between SL and conventional…
Softmax Loss (SL) is being increasingly adopted for recommender systems (RS) as it has demonstrated better performance, robustness and fairness. Yet in implicit-feedback, a single global temperature and equal treatment of uniformly sampled…
This paper illustrates the central role of loss functions in data-driven decision making, providing a comprehensive survey on their influence in cost-sensitive classification (CSC) and reinforcement learning (RL). We demonstrate how…
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…
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias, wherein negative samples may encompass similar semantics (\eg labels). However, existing theories fall short in providing explanations for this…
Inspired by the success of contrastive learning, we systematically examine recommendation losses, including listwise (softmax), pairwise (BPR), and pointwise (MSE and CCL) losses. In this endeavor, we introduce InfoNCE+, an optimized…
This paper addresses the problem of visual feature representation learning with an aim to improve the performance of end-to-end reinforcement learning (RL) models. Specifically, a novel architecture is proposed that uses a heterogeneous…
In Self-Supervised Learning (SSL), various pretext tasks are designed for learning feature representations through contrastive loss. However, previous studies have shown that this loss is less tolerant to semantically similar samples due to…
We study a family of loss functions named label-distributionally robust (LDR) losses for multi-class classification that are formulated from distributionally robust optimization (DRO) perspective, where the uncertainty in the given label…
Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been…
The development of deep convolutional neural network architecture is critical to the improvement of image classification task performance. Many image classification studies use deep convolutional neural network and focus on modifying the…
Large language models (LLMs) have gained much attention in the recommendation community; some studies have observed that LLMs, fine-tuned by the cross-entropy loss with a full softmax, could achieve state-of-the-art performance already.…
The development of deep convolutional neural network architecture is critical to the improvement of image classification task performance. A lot of studies of image classification based on deep convolutional neural network focus on the…
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…
While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…
The cross-entropy softmax loss is the primary loss function used to train deep neural networks. On the other hand, the focal loss function has been demonstrated to provide improved performance when there is an imbalance in the number of…
Self-supervised learning (SSL) has recently achieved great success in mining the user-item interactions for collaborative filtering. As a major paradigm, contrastive learning (CL) based SSL helps address data sparsity in Web platforms by…
We study constrained reinforcement learning (CRL) from a novel perspective by setting constraints directly on state density functions, rather than the value functions considered by previous works. State density has a clear physical and…
This paper presents an analysis regarding an influence of the Distance Metric Learning (DML) loss functions on the supervised fine-tuning of the language models for classification tasks. We experimented with known datasets from SentEval…