相关论文: Enhancing Training Data Attribution with Represent…

The goal of predictive data attribution is to estimate how adding or removing a given set of training datapoints will affect model predictions. In convex settings, this goal is straightforward (i.e., via the infinitesimal jackknife). In…

Materials property prediction models are usually evaluated using random splitting of datasets into training and test datasets, which not only leads to over-estimated performance due to inherent redundancy, typically existent in material…

We use information-theoretic tools to derive a novel analysis of Multi-source Domain Adaptation (MDA) from the representation learning perspective. Concretely, we study joint distribution alignment for supervised MDA with few target labels…

Aerodynamic surrogate models are increasingly used to replace repeated high-fidelity CFD evaluations in many-query design settings, but current approaches still face two important limitations: they often scale poorly to the very large…

Data Augmentation is a common technique used to enhance the performance of deep learning models by expanding the training dataset. Automatic Data Augmentation (ADA) methods are getting popular because of their capacity to generate policies…

The current Air Traffic Management (ATM) system worldwide has reached its limits in terms of predictability, efficiency and cost effectiveness. Different initiatives worldwide propose trajectory-oriented transformations that require high…

As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in…

As an effective approach to quantify how training samples influence test sample, data attribution is crucial for understanding data and model and further enhance the transparency of machine learning models. We find that prevailing data…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on…

Diffusion models have demonstrated their capabilities in modeling trajectories of multi-tasks. However, existing multi-task planners or policies typically rely on task-specific demonstrations via multi-task imitation, or require…

Instruction tuning has unlocked powerful capabilities in large language models (LLMs), effectively using combined datasets to develop generalpurpose chatbots. However, real-world applications often require a specialized suite of skills…

Unsupervised domain adaption (UDA) is a transfer learning task where the data and annotations of the source domain are available but only have access to the unlabeled target data during training. Most previous methods try to minimise the…

The goal of this paper is to optimize the training process of diffusion-based text-to-speech models. While recent studies have achieved remarkable advancements, their training demands substantial time and computational costs, largely due to…

While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interaction with the environment, learning from limited interaction remains a key challenge. We posit that an…

In this paper, a deep reinforcement learning (DRL) method is proposed to address the problem of UAV navigation in an unknown environment. However, DRL algorithms are limited by the data efficiency problem as they typically require a huge…

Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and…

Prioritized Experience Replay (PER) enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. However, this non-uniform sampling method shifts the state-action distribution that…

Widespread adoption of deep models has motivated a pressing need for approaches to interpret network outputs and to facilitate model debugging. Instance attribution methods constitute one means of accomplishing these goals by retrieving…

Training autonomous agents with sparse rewards is a long-standing problem in online reinforcement learning (RL), due to low data efficiency. Prior work overcomes this challenge by extracting useful knowledge from offline data, often…