Related papers: Self-Sampling Training and Evaluation for the Accu…

In this work, we observe a counterintuitive phenomenon in self-supervised learning (SSL): longer training may impair the performance of dense prediction tasks (e.g., semantic segmentation). We refer to this phenomenon as Self-supervised…

Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that often suffers from the problem of "confirmation bias" that…

Previous debiasing studies utilize unbiased data to make supervision of model training. They suffer from the high trial risks and experimental costs to obtain unbiased data. Recent research attempts to use invariant learning to detach the…

Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct…

It is well known that for some tasks, labeled data sets may be hard to gather. Therefore, we wished to tackle here the problem of having insufficient training data. We examined learning methods from unlabeled data after an initial training…

Multimedia content is of predominance in the modern Web era. In real scenarios, multiple modalities reveal different aspects of item attributes and usually possess different importance to user purchase decisions. However, it is difficult…

Classifiers are biased when trained on biased datasets. As a remedy, we propose Learning to Split (ls), an algorithm for automatic bias detection. Given a dataset with input-label pairs, ls learns to split this dataset so that predictors…

Self-supervised learning (SSL), which can automatically generate ground-truth samples from raw data, holds vast potential to improve recommender systems. Most existing SSL-based methods perturb the raw data graph with uniform node/edge…

Improving recommendation systems (RS) can greatly enhance the user experience across many domains, such as social media. Many RS utilize embedding-based retrieval (EBR) approaches to retrieve candidates for recommendation. In an EBR system,…

Existing sequential recommendation methods rely on large amounts of training data and usually suffer from the data sparsity problem. To tackle this, the pre-training mechanism has been widely adopted, which attempts to leverage large-scale…

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously…

Code generation is typically trained in the primal space of programs: a model produces a candidate solution and receives sparse execution feedback, often a single pass/fail bit. Test-time scaling enriches the inference procedure by sampling…

Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted) and model utility (how good is the performance on accepted…

The scarcity of high-quality training data presents a fundamental bottleneck to scaling machine learning models. This challenge is particularly acute in recommendation systems, where extreme sparsity in user interactions leads to rugged…

An effective ranking model usually requires a large amount of training data to learn the relevance between documents and queries. User clicks are often used as training data since they can indicate relevance and are cheap to collect, but…

Given a supervised machine learning problem where the training set has been subject to a known sampling bias, how can a model be trained to fit the original dataset? We achieve this through the Bayesian inference framework by altering the…

Simplicity bias poses a significant challenge in neural networks, often leading models to favor simpler solutions and inadvertently learn decision rules influenced by spurious correlations. This results in biased models with diminished…

In continual instruction tuning (CIT) scenarios, where new instruction tuning data continuously arrive in an online streaming manner, training delays from large-scale data significantly hinder real-time adaptation. Data selection can…

We propose a semi-supervised text classifier based on self-training using one positive and one negative property of neural networks. One of the weaknesses of self-training is the semantic drift problem, where noisy pseudo-labels accumulate…

Semi-supervised learning provides a solution to reduce the dependency of machine learning on labeled data. As one of the efficient semi-supervised techniques, self-training (ST) has received increasing attention. Several advancements have…