Related papers: Sebra: Debiasing Through Self-Guided Bias Ranking
Bias is a common problem inherent in recommender systems, which is entangled with users' preferences and poses a great challenge to unbiased learning. For debiasing tasks, the doubly robust (DR) method and its variants show superior…
Learning from positive and unlabeled data is known as positive-unlabeled (PU) learning in literature and has attracted much attention in recent years. One common approach in PU learning is to sample a set of pseudo-negatives from the…
Sequential recommendation is often considered as a generative task, i.e., training a sequential encoder to generate the next item of a user's interests based on her historical interacted items. Despite their prevalence, these methods…
Estimation using pooled sampling has long been an area of interest in the group testing literature. Such research has focused primarily on the assumed use of fixed sampling plans (i), although some recent papers have suggested alternative…
Classification and probability estimation are fundamental tasks with broad applications across modern machine learning and data science, spanning fields such as biology, medicine, engineering, and computer science. Recent development of…
Neural networks produced by standard training are known to suffer from poor accuracy on rare subgroups despite achieving high accuracy on average, due to the correlations between certain spurious features and labels. Previous approaches…
Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of…
Multimodal Large Language Models (MLLMs) have shown substantial capabilities in integrating visual and textual information, yet frequently rely on spurious correlations, undermining their robustness and generalization in complex multimodal…
Semi-supervised semantic segmentation learns from small amounts of labelled images and large amounts of unlabelled images, which has witnessed impressive progress with the recent advance of deep neural networks. However, it often suffers…
Learning-to-rank (LTR) is a set of supervised machine learning algorithms that aim at generating optimal ranking order over a list of items. A lot of ranking models have been studied during the past decades. And most of them treat each…
Positive and Unlabeled (PU) learning, a binary classification model trained with only positive and unlabeled data, generally suffers from overfitted risk estimation due to inconsistent data distributions. To address this, we introduce a…
Sequential recommender systems train their models based on a large amount of implicit user feedback data and may be subject to biases when users are systematically under/over-exposed to certain items. Unbiased learning based on inverse…
We present a novel approach to learn binary classifiers when only positive and unlabeled instances are available (PU learning). This problem is routinely cast as a supervised task with label noise in the negative set. We use an ensemble of…
In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent…
In most real-world recommender systems, the observed rating data are subject to selection bias, and the data are thus missing-not-at-random. Developing a method to facilitate the learning of a recommender with biased feedback is one of the…
Pretrained language models have been shown to exhibit biases and social stereotypes. Prior work on debiasing these models has largely focused on modifying embedding spaces during pretraining, which is not scalable for large models.…
Image classification is an essential part of computer vision which assigns a given input image to a specific category based on the similarity evaluation within given criteria. While promising classifiers can be obtained through deep…
Deep learning models can suffer from severe performance degradation when relying on spurious correlations between input features and labels, making the models perform well on training data but have poor prediction accuracy for minority…
Despite its flexibility to learn diverse inductive biases in machine learning programs, meta learning (i.e., learning to learn) has long been recognized to suffer from poor scalability due to its tremendous compute/memory costs, training…
In the field of multimodal sentiment analysis (MSA), a few studies have leveraged the inherent modality correlation information stored in samples for self-supervised learning. However, they feed the training pairs in a random order without…