Related papers: Rethinking Missing Data: Aleatoric Uncertainty-Awa…
Recommendation systems often rely on implicit feedback, where only positive user-item interactions can be observed. Negative sampling is therefore crucial to provide proper negative training signals. However, existing methods tend to…
The ubiquity of implicit feedback makes it indispensable for building recommender systems. However, it does not actually reflect the actual satisfaction of users. For example, in E-commerce, a large portion of clicks do not translate to…
In recommendation systems, items are likely to be exposed to various users and we would like to learn about the familiarity of a new user with an existing item. This can be formulated as an anomaly detection (AD) problem distinguishing…
Causality-based recommendation systems focus on the causal effects of user-item interactions resulting from item exposure (i.e., which items are recommended or exposed to the user), as opposed to conventional correlation-based…
With the growing privacy concerns in recommender systems, recommendation unlearning, i.e., forgetting the impact of specific learned targets, is getting increasing attention. Existing studies predominantly use training data, i.e., model…
Active Learning (AL) aims to enhance the performance of deep models by selecting the most informative samples for annotation from a pool of unlabeled data. Despite impressive performance in closed-set settings, most AL methods fail in…
The quick and pervasive infiltration of decision support systems, artificial intelligence, and data mining in consumer electronics and everyday life in general has been significant in recent years. Fields such as UX have been facilitating…
In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels,…
The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discussions of these ideas and suggest this stems from the…
To generate accurate and reliable predictions, modern AI systems need to combine data from multiple modalities, such as text, images, audio, spreadsheets, and time series. Multi-modal data introduces new opportunities and challenges for…
Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches…
Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, this framework triggers clarification questions when detecting…
Recommender systems are one of the most successful applications of data mining and machine learning technology in practice. Academic research in the field is historically often based on the matrix completion problem formulation, where for…
General recommender systems deliver personalized services by learning user and item representations, with the central challenge being how to capture latent user preferences. However, representations derived from sparse interactions often…
Data annotation is essential for supervised learning, yet producing accurate, unbiased, and scalable labels remains challenging as datasets grow in size and modality. Traditional human-centric pipelines are costly, slow, and prone to…
The inability of artificial neural networks to assess the uncertainty of their predictions is an impediment to their widespread use. We distinguish two types of learnable uncertainty: model uncertainty due to a lack of training data and…
In large-scale recommendation systems, the vast array of items makes it infeasible to obtain accurate user preferences for each product, resulting in a common issue of missing labels. Typically, only items previously recommended to users…
Recommender systems have been gaining increasing research attention over the years. Most existing recommendation methods focus on capturing users' personalized preferences through historical user-item interactions, which may potentially…
High-quality labeled data is essential for training robust machine learning models, yet obtaining annotations at scale remains expensive. AI-assisted annotation has therefore become standard in large-scale labeling workflows. However, in…
In safety-critical applications like medical diagnosis, certainty associated with a model's prediction is just as important as its accuracy. Consequently, uncertainty estimation and reduction play a crucial role. Uncertainty in predictions…