Related papers: A Unified Deep Model of Learning from both Data an…

Predicting future resource demand in Cloud Computing is essential for optimizing the trade-off between serving customers' requests efficiently and minimizing the provisioning cost. Modelling prediction uncertainty is also desirable to…

Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available by leveraging information from annotated data in a source domain. Most deep UDA approaches operate in a…

Approximate machine unlearning (AMU) enables models to `forget' specific training data through specialized fine-tuning on a retained (and forget) subset of training set. However, processing this large retained subset still dominates…

While recent automated data augmentation methods lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human priors. In this work, instead of fixing a set of hand-picked…

Weather forecasting is fundamentally challenged by the chaotic nature of the atmosphere, necessitating probabilistic approaches to quantify uncertainty. While traditional ensemble prediction (EPS) addresses this through computationally…

Learned cardinality estimation requires accurate model designs to capture the local characteristics of probability distributions. However, existing models may fail to accurately capture complex, multilateral dependencies between attributes.…

Federated and Continual Learning have emerged as potential paradigms for the robust and privacy-aware use of Deep Learning in dynamic environments. However, Client Drift and Catastrophic Forgetting are fundamental obstacles to guaranteeing…

Modern image retrieval systems increasingly rely on the use of deep neural networks to learn embedding spaces in which distance encodes the relevance between a given query and image. In this setting, existing approaches tend to emphasize…

LLM-based universal information extraction (UIE) methods often rely on additional information beyond the original training data, which increases training complexity yet often yields limited gains. To address this, we propose ProUIE, a…

Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings, in which the…

We develop BatchBALD, a tractable approximation to the mutual information between a batch of points and model parameters, which we use as an acquisition function to select multiple informative points jointly for the task of deep Bayesian…

Medical knowledge extraction methods based on edge computing deploy deep learning models on edge devices to achieve localized entity and relation extraction. This approach avoids transferring substantial sensitive data to cloud data…

Entity alignment (EA) which links equivalent entities across different knowledge graphs (KGs) plays a crucial role in knowledge fusion. In recent years, graph neural networks (GNNs) have been successfully applied in many embedding-based EA…

Time-series analysis plays a pivotal role across a range of critical applications, from finance to healthcare, which involves various tasks, such as forecasting and classification. To handle the inherent complexities of time-series data,…

We present a comparison of methods for uncertainty quantification (UQ) in deep learning algorithms in the context of a simple physical system. Three of the most common uncertainty quantification methods - Bayesian Neural Networks (BNN),…

Failure of machine learning models to generalize to new data is a core problem limiting the reliability of AI systems, partly due to the lack of simple and robust methods for comparing new data to the original training dataset. We propose a…

We are concerned with learning models that generalize well to different \emph{unseen} domains. We consider a worst-case formulation over data distributions that are near the source domain in the feature space. Only using training data from…

Selectivity estimation - the problem of estimating the result size of queries - is a fundamental problem in databases. Accurate estimation of query selectivity involving multiple correlated attributes is especially challenging. Poor…

Deep learning models trained on medical images from a source domain (e.g. imaging modality) often fail when deployed on images from a different target domain, despite imaging common anatomical structures. Deep unsupervised domain adaptation…

Deploying large language model inference remains challenging due to their high computational overhead. Early exit optimizes model inference by adaptively reducing the number of inference layers. Current methods typically train internal…