Related papers: MGDA: Model-based Goal Data Augmentation for Offli…

Graph Few-Shot Class-Incremental Learning (GFSCIL) enables models to continually learn from limited samples of novel tasks after initial training on a large base dataset. Existing GFSCIL approaches typically utilize Prototypical Networks…

Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for optimal DA policies with reinforcement learning. However,…

Real-world decision-making tasks typically occur in complex and open environments, posing significant challenges to reinforcement learning (RL) agents' exploration efficiency and long-horizon planning capabilities. A promising approach is…

Recent advances in commonsense reasoning depend on large-scale human-annotated training data to achieve peak performance. However, manual curation of training examples is expensive and has been shown to introduce annotation artifacts that…

This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers. These algorithms performed competitively across…

In goal-conditioned offline reinforcement learning, an agent learns from previously collected data to go to an arbitrary goal. Since the offline data only contains a finite number of trajectories, a main challenge is how to generate more…

This paper presents an innovative approach to enhancing few-shot learning by integrating data augmentation with model fine-tuning in a framework designed to tackle the challenges posed by small-sample data. Recognizing the critical…

Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however, human preferences…

Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are not effective enough. In this work, we design a novel data…

Graph contrastive learning (GCL) has emerged as an effective tool for learning unsupervised representations of graphs. The key idea is to maximize the agreement between two augmented views of each graph via data augmentation. Existing GCL…

Continuous efforts are being made to advance anomaly detection in various manufacturing processes to increase the productivity and safety of industrial sites. Deep learning replaced rule-based methods and recently emerged as a promising…

We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. In this setting, aligning style with high task performance is particularly challenging due to…

In recent years, there has been a growing interest in combining learnable modules with numerical optimization to solve low-level vision tasks. However, most existing approaches focus on designing specialized schemes to generate…

This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with…

Graph contrastive learning (GCL) is a popular method for leaning graph representations by maximizing the consistency of features across augmented views. Traditional GCL methods utilize single-perspective i.e. data or model-perspective)…

We propose generative multitask learning (GMTL), a simple and scalable approach to causal representation learning for multitask learning. Our approach makes a minor change to the conventional multitask inference objective, and improves…

Image data augmentation constitutes a critical methodology in modern computer vision tasks, since it can facilitate towards enhancing the diversity and quality of training datasets; thereby, improving the performance and robustness of…

Mini-batch sub-sampling (MBSS) is favored in deep neural network training to reduce the computational cost. Still, it introduces an inherent sampling error, making the selection of appropriate learning rates challenging. The sampling errors…

Automatic machine learning (\AML) is a family of techniques to automate the process of training predictive models, aiming to both improve performance and make machine learning more accessible. While many recent works have focused on aspects…

When dealing with real-world optimization problems, decision-makers usually face high levels of uncertainty associated with partial information, unknown parameters, or complex relationships between these and the problem decision variables.…