Related papers: Duet: efficient and scalable hybriD neUral rElatio…

Uncertainty quantification is critical for deploying deep neural networks (DNNs) in real-world applications. An Auxiliary Uncertainty Estimator (AuxUE) is one of the most effective means to estimate the uncertainty of the main task…

Neural link predictors learn distributed representations of entities and relations in a knowledge graph. They are remarkably powerful in the link prediction and knowledge base completion tasks, mainly due to the learned representations that…

We consider the estimation of Dirichlet Process Mixture Models (DPMMs) in distributed environments, where data are distributed across multiple computing nodes. A key advantage of Bayesian nonparametric models such as DPMMs is that they…

Cardinality estimation is a key component of database query optimization. Recent studies have demonstrated that learned cardinality estimation techniques can surpass traditional methods in accuracy. However, a significant barrier to their…

The rapid advancements in machine learning techniques have led to significant achievements in various real-world robotic tasks. These tasks heavily rely on fast and energy-efficient inference of deep neural network (DNN) models when…

Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…

We describe a new cardinality estimation algorithm that is extremely space-efficient. It applies one of three novel estimators to the compressed state of the Flajolet-Martin-85 coupon collection process. In an apples-to-apples empirical…

Hybrid fault models are known to be an effective means for enhancing the robustness of consensus-based replicated systems. However, existing hybridization approaches suffer from limited flexibility with regard to the composition of…

Traditional methods for matching in causal inference are impractical for high-dimensional datasets. They suffer from the curse of dimensionality: exact matching and coarsened exact matching find exponentially fewer matches as the input…

Due to high accuracy, BERT-like models have been widely adopted by text mining and web searching. However, large BERT-like models suffer from inefficient online inference, facing the following two problems on GPUs: (1) their high accuracy…

Recently, Deep Neural Networks (DNNs) have recorded great success in handling medical and other complex classification tasks. However, as the sizes of a DNN model and the available dataset increase, the training process becomes more complex…

Machine unlearning in learned cardinality estimation (CE) systems presents unique challenges due to the complex distributional dependencies in multi-table relational data. Specifically, data deletion, a core component of machine unlearning,…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

As the data size in Machine Learning fields grows exponentially, it is inevitable to accelerate the computation by utilizing the ever-growing large number of available cores provided by high-performance computing hardware. However, existing…

Despite the remarkable progress made by learning based stereo matching algorithms, one key challenge remains unsolved. Current state-of-the-art stereo models are mostly based on costly 3D convolutions, the cubic computational complexity and…

Deep learning has been used to demonstrate end-to-end neural network learning for autonomous vehicle control from raw sensory input. While LiDAR sensors provide reliably accurate information, existing end-to-end driving solutions are mainly…

Host cardinality is one of the important attributes in the field of network research. The cardinality estimation under sliding time window has become a research hotspot in recent years because of its high accuracy and small delay. This kind…

Pre-trained vision-language models like CLIP have shown powerful zero-shot inference ability via image-text matching and prove to be strong few-shot learners in various downstream tasks. However, in real-world scenarios, adapting CLIP to…

This paper derives a discrete dual problem for a prototypical hybrid high-order method for convex minimization problems. The discrete primal and dual problem satisfy a weak convex duality that leads to a priori error estimates with…

We study the problem of dataset distillation - creating a small set of synthetic examples capable of training a good model. In particular, we study the problem of label distillation - creating synthetic labels for a small set of real…