Related papers: Inverse Learning with Extremely Sparse Feedback fo…

Nowadays, recommender systems already impact almost every facet of peoples lives. To provide personalized high quality recommendation results, conventional systems usually train pointwise rankers to predict the absolute value of objectives…

In Imitation Learning (IL), utilizing suboptimal and heterogeneous demonstrations presents a substantial challenge due to the varied nature of real-world data. However, standard IL algorithms consider these datasets as homogeneous, thereby…

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover,…

Gradient boosting remains a strong and widely used method for tabular data learning, but its performance often degrades when training labels are noisy. This behavior is largely related to the way boosting algorithms emphasize samples with…

In this dissertation, we propose a systemic framework that prioritizes informative features and examples to enhance each stage of the development process. Specifically, we prioritize informative features and examples and improve the…

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the…

Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies…

Gradient descent can be surprisingly good at optimizing deep neural networks without overfitting and without explicit regularization. We find that the discrete steps of gradient descent implicitly regularize models by penalizing gradient…

While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of data annotation, active learning has been proposed to…

Like humans, deep networks have been shown to learn better when samples are organized and introduced in a meaningful order or curriculum. Conventional curriculum learning schemes introduce samples in their order of difficulty. This forces…

Traditional supervised learning requires ground truth labels for the training data, whose collection can be difficult in many cases. Recently, crowdsourcing has established itself as an efficient labeling solution through resorting to…

Deep learning based models have excelled in many computer vision tasks and appear to surpass humans' performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large…

Anomaly detection plays a critical role in Autonomous Vehicles (AVs) by identifying unusual behaviors through perception systems that could compromise safety and lead to hazardous situations. Current approaches, which often rely on…

Low-resource Relation Extraction (LRE) aims to extract relation facts from limited labeled corpora when human annotation is scarce. Existing works either utilize self-training scheme to generate pseudo labels that will cause the gradual…

Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…

Rewards serve as a measure of user satisfaction and act as a limiting factor in interactive recommender systems. In this research, we focus on the problem of learning to reward (LTR), which is fundamental to reinforcement learning. Previous…

Interactive reinforcement learning has shown promise in learning complex robotic tasks. However, the process can be human-intensive due to the requirement of a large amount of interactive feedback. This paper presents a new method that uses…

Offline model-based optimization aims to find a design that maximizes a property of interest using only an offline dataset, with applications in robot, protein, and molecule design, among others. A prevalent approach is gradient ascent,…

Most recent machine learning research focuses on developing new classifiers for the sake of improving classification accuracy. With many well-performing state-of-the-art classifiers available, there is a growing need for understanding…

Transfer learning aims to improve learning in target domain by borrowing knowledge from a related but different source domain. To reduce the distribution shift between source and target domains, recent methods have focused on exploring…