Related papers: Learning Defect Prediction from Unrealistic Data

Multitask learning is widely used in practice to train a low-resource target task by augmenting it with multiple related source tasks. Yet, naively combining all the source tasks with a target task does not always improve the prediction…

Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works address this problem by pre-training visual representations on large-scale but…

In safety-critical applications, language models should be able to characterize their uncertainty with meaningful probabilities. Many uncertainty quantification approaches require supervised data; however, finding suitable unseen…

Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a networked sample because two or more training examples may…

Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as "memory" for the trained models and help them generalize well on unseen data. However, in absence of training data, the utility of a…

Mislabeled, duplicated, or biased data in real-world scenarios can lead to prolonged training and even hinder model convergence. Traditional solutions prioritizing easy or hard samples lack the flexibility to handle such a variety…

Pretrained language models (LMs) perform well on many tasks even when learning from a few examples, but prior work uses many held-out examples to tune various aspects of learning, such as hyperparameters, training objectives, and natural…

Imitation learning from large multi-task demonstration datasets has emerged as a promising path for building generally-capable robots. As a result, 1000s of hours have been spent on building such large-scale datasets around the globe.…

Recent research on robustness has revealed significant performance gaps between neural image classifiers trained on datasets that are similar to the test set, and those that are from a naturally shifted distribution, such as sketches,…

It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are…

Advances in deep learning systems have allowed large models to match or surpass human accuracy on a number of skills such as image classification, basic programming, and standardized test taking. As the performance of the most capable…

Machine learning offers attractive solutions to challenging image processing tasks. Tedious development and parametrization of algorithmic solutions can be replaced by training a convolutional neural network or a random forest with a high…

Software vulnerabilities pose significant security threats, requiring effective mitigation. While Automated Program Repair (APR) has advanced in fixing general bugs, vulnerability patching, a security-critical aspect of APR remains…

Unlearnable Examples (UEs) serve as a data protection strategy that generates imperceptible perturbations to mislead models into learning spurious correlations instead of underlying semantics. In this paper, we uncover a fundamental…

Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is…

In training neural networks, it is common practice to use partial gradients computed over batches, mostly very small subsets of the training set. This approach is motivated by the argument that such a partial gradient is close to the true…

We consider learning a predictive model to be subsequently used for a given downstream task (described by an algorithm) that requires access to the model evaluation. This task need not be prediction, and this situation is frequently…

Machine Learning (ML)-based network models provide fast and accurate predictions for complex network behaviors but require substantial training data. Collecting such data from real networks is often costly and limited, especially for…

Deep Learning methods have significantly advanced various data-driven tasks such as regression, classification, and forecasting. However, much of this progress has been predicated on the strong but often unrealistic assumption that training…

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…