Related papers: Causal Negative Sampling via Diffusion Model for O…

In implicit collaborative filtering (CF) task of recommender systems, recent works mainly focus on model structure design with promising techniques like graph neural networks (GNNs). Effective and efficient negative sampling methods that…

Graph Neural Networks (GNNs)-based recommendation algorithms typically assume that training and testing data are drawn from independent and identically distributed (IID) spaces. However, this assumption often fails in the presence of…

Feature selection is fundamental to robust data-centric AI, but most existing methods optimize predictive performance under a single data distribution. This often selects spurious features that fail under distribution shifts. Motivated by…

Negative sampling is significant for training sequential recommendation models under implicit feedback. The predominant strategy, self-guided hard negative sampling, selects negatives based on the model's current state but suffers from…

Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-art performance.…

Over the past few years, several approaches utilizing score-based diffusion have been proposed to sample from probability distributions, that is without having access to exact samples and relying solely on evaluations of unnormalized…

Negative sampling is essential for implicit collaborative filtering to provide proper negative training signals so as to achieve desirable performance. We experimentally unveil a common limitation of all existing negative sampling methods…

Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (OOD) detection of image inputs. However, these methods struggle to detect OOD inputs that share…

Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample…

Recommender systems leverage extensive user interaction data to model preferences; however, directly modeling these data may introduce biases that disproportionately favor popular items. In this paper, we demonstrate that popularity bias…

Social recommendation has emerged as a powerful approach to enhance personalized recommendations by leveraging the social connections among users, such as following and friend relations observed in online social platforms. The fundamental…

As Classifier-Free Guidance (CFG) has proven effective in conditional diffusion model sampling for improved condition alignment, many applications use a negated CFG term to filter out unwanted features from samples. However, simply negating…

Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate samples from the data distribution are then obtained by…

Predicting counterfactual distributions in complex dynamical systems is essential for scientific modeling and decision-making in domains such as public health and medicine. However, existing methods often rely on point estimates or purely…

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based…

Predicting counterfactual outcomes in longitudinal data, where sequential treatment decisions heavily depend on evolving patient states, is critical yet notoriously challenging due to complex time-dependent confounding and inadequate…

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…

Denoising Diffusion Probabilistic Models (DDPMs) have gained great attention in adversarial purification. Current diffusion-based works focus on designing effective condition-guided mechanisms while ignoring a fundamental problem, i.e., the…

Out-of-Distribution (OOD) generalization has become a primary metric for evaluating image analysis systems. Since deep learning models tend to capture domain-specific context, they often develop shortcut dependencies on these non-causal…

Classifier-Free Guidance (CFG) is a widely used technique for improving conditional diffusion models by linearly combining the outputs of conditional and unconditional denoisers. While CFG enhances visual quality and improves alignment with…