Related papers: Diversifying Dialog Generation via Adaptive Label …

Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits. Often, performance gains and improved generalization can be…

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label…

Dialogue generation models face the challenge of producing generic and repetitive responses. Unlike previous augmentation methods that mostly focus on token manipulation and ignore the essential variety within a single sample using hard…

Training neural networks with one-hot target labels often results in overconfidence and overfitting. Label smoothing addresses this issue by perturbing the one-hot target labels by adding a uniform probability vector to create a regularized…

We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent analysis on a critical issue from label distribution mismatch…

The generalization and learning speed of a multi-class neural network can often be significantly improved by using soft targets that are a weighted average of the hard targets and the uniform distribution over labels. Smoothing the labels…

This paper describes a method of domain adaptive training for semantic segmentation using multiple source datasets that are not necessarily relevant to the target dataset. We propose a soft pseudo-label generation method by integrating…

Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains. To handle large-scale graphs, most of the existing…

Human capability to anticipate near future from visual observations and non-verbal cues is essential for developing intelligent systems that need to interact with people. Several research areas, such as human-robot interaction (HRI),…

Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that can be interpreted in multiple ways, over-confidently…

Despite the success of deep neural network (DNN) on sequential data (i.e., scene text and speech) recognition, it suffers from the over-confidence problem mainly due to overfitting in training with the cross-entropy loss, which may make the…

Training modern neural networks is an inherently noisy process that can lead to high \emph{prediction churn} -- disagreements between re-trainings of the same model due to factors such as randomization in the parameter initialization and…

We show that variational learning naturally induces an adaptive label smoothing where label noise is specialized for each example. Such label-smoothing is useful to handle examples with labeling errors and distribution shifts, but designing…

Label smoothing is widely used in deep neural networks for multi-class classification. While it enhances model generalization and reduces overconfidence by aiming to lower the probability for the predicted class, it distorts the predicted…

Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performance. When allocating…

Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscalibrated predictions,…

As a prominent challenge in addressing real-world issues within a dynamic environment, label shift, which refers to the learning setting where the source (training) and target (testing) label distributions do not match, has recently…

Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different sources based on their relations. In this paper, we…

Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…

Out-of-distribution (OOD) detection, which aims to distinguish unknown classes from known classes, has received increasing attention recently. A main challenge within is the unavailable of samples from the unknown classes in the training…