Related papers: Preparation Meets Opportunity: Enhancing Data Prep…

Big data has found applications in multiple domains. One of the largest sources of textual big data is scientific documents and papers. Big scholarly data have been used in numerous ways to create innovative applications such as…

Machine learning has significant potential for optimizing various industrial processes. However, data acquisition remains a major challenge as it is both time-consuming and costly. Synthetic data offers a promising solution to augment…

Meta learning is a promising technique for solving few-shot fault prediction problems, which have attracted the attention of many researchers in recent years. Existing meta-learning methods for time series prediction, which predominantly…

Multi-task clustering (MTC) has attracted a lot of research attentions in machine learning due to its ability in utilizing the relationship among different tasks. Despite the success of traditional MTC models, they are either easy to stuck…

Mobile edge computing (MEC) networks bring computing and storage capabilities closer to edge devices, which reduces latency and improves network performance. However, to further reduce transmission and computation costs while satisfying…

Secure multi-party computation (MPC) facilitates privacy-preserving computation between multiple parties without leaking private information. While most secure deep learning techniques utilize MPC operations to achieve feasible…

Multi-access Edge Computing (MEC) is a type of network architecture that provides cloud computing capabilities at the edge of the network. We consider the use case of video surveillance for an university campus running on a 5G-MEC…

Machine learning models are routinely integrated into process mining pipelines to carry out tasks like data transformation, noise reduction, anomaly detection, classification, and prediction. Often, the design of such models is based on…

Nowadays deep learning-based methods have achieved a remarkable progress at the image classification task among a wide range of commonly used datasets (ImageNet, CIFAR, SVHN, Caltech 101, SUN397, etc.). SOTA performance on each of the…

Distributed Machine Learning (DML) systems are utilized to enhance the speed of model training in data centers (DCs) and edge nodes. The Parameter Server (PS) communication architecture is commonly employed, but it faces severe long-tail…

Memory latencies and bandwidth are major factors, limiting system performance and scalability. Modern CPUs aim at hiding latencies by employing large caches, out-of-order execution, or complex hardware prefetchers. However, software-based…

In data containing heterogeneous subpopulations, classification performance benefits from incorporating the knowledge of cluster structure in the classifier. Previous methods for such combined clustering and classification either 1) are…

We present FFCV, a library for easy and fast machine learning model training. FFCV speeds up model training by eliminating (often subtle) data bottlenecks from the training process. In particular, we combine techniques such as an efficient…

Distributed machine learning (DML) technology makes it possible to train large neural networks in a reasonable amount of time. Meanwhile, as the computing power grows much faster than network capacity, network communication has gradually…

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training…

Synthetic data augmentation has emerged as a promising solution when pre-training is constrained by data rather than compute. We study how to design synthetic data algorithms that achieve better loss scaling: not only lowering loss at…

The rapid growth of dataset scales has been a key driver in advancing deep learning research. However, as dataset scale increases, the training process becomes increasingly inefficient due to the presence of low-value samples, including…

Training large foundation models costs hundreds of millions of dollars, making deployment optimization critical. Current approaches require machine learning engineers to manually craft training recipes through error-prone trial-and-error on…

Performance models are essential for automatic code optimization, enabling compilers to predict the effects of code transformations on performance and guide search for optimal transformations. Building state-of-the-art performance models…

Cache prefetcher greatly eliminates compulsory cache misses, by fetching data from slower memory to faster cache before it is actually required by processors. Sophisticated prefetchers predict next use cache line by repeating program's…