相关论文: Exploring Query Efficient Data Generation towards …

The increasing reliance on large language models (LLMs) such as ChatGPT in various fields emphasizes the importance of ``prompt engineering,'' a technology to improve the quality of model outputs. With companies investing significantly in…

Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their models that could facilitate theft, including uncertainty…

Model-based testing (MBT) provides an automated approach for finding discrepancies between software models and their implementation. If we want to incorporate MBT into the fast and iterative software development process that is Continuous…

We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i.e. in a zero-shot setting. Many dense retrieval models are readily available. Each model…

Real-world data is often incomplete and contains missing values. To train accurate models over real-world datasets, users need to spend a substantial amount of time and resources imputing and finding proper values for missing data items. In…

Unlike traditional central training, federated learning (FL) improves the performance of the global model by sharing and aggregating local models rather than local data to protect the users' privacy. Although this training approach appears…

In many practical real-world applications, data missing is a very common phenomenon, making the development of data-driven artificial intelligence theory and technology increasingly difficult. Data completion is an important method for…

Sufficient supervised information is crucial for any machine learning models to boost performance. However, labeling data is expensive and sometimes difficult to obtain. Active learning is an approach to acquire annotations for data from a…

Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding examples which satisfy…

Machine Learning-as-a-Service (MLaaS) has become a widespread paradigm, making even the most complex machine learning models available for clients via e.g. a pay-per-query principle. This allows users to avoid time-consuming processes of…

Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human…

Graph Neural Networks (GNNs) achieve high performance in various real-world applications, such as drug discovery, traffic states prediction, and recommendation systems. The fact that building powerful GNNs requires a large amount of…

Traditional model-free feature selection methods treat each feature independently while disregarding the interrelationships among features, which leads to relatively poor performance compared with the model-aware methods. To address this…

Accurately estimating model performance poses a significant challenge, particularly in scenarios where the source and target domains follow different data distributions. Most existing performance prediction methods heavily rely on the…

Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. Robustness means the model fine-tuned by concept erasure methods resists reactivation of erased…

The design dataset is the backbone of data-driven design. Ideally, the dataset should be fairly distributed in both shape and property spaces to efficiently explore the underlying relationship. However, the classical experimental design…

Consider learning a generative model for time-series data. The sequential setting poses a unique challenge: Not only should the generator capture the conditional dynamics of (stepwise) transitions, but its open-loop rollouts should also…

Ensuring fairness in machine learning remains a significant challenge, as models often inherit biases from their training data. Generative models have recently emerged as a promising approach to mitigate bias at the data level while…

This work presents Fair4Free, a novel generative model to generate synthetic fair data using data-free distillation in the latent space. Fair4Free can work on the situation when the data is private or inaccessible. In our approach, we first…

Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined…