Related papers: FeatureBox: Feature Engineering on GPUs for Massiv…

Discrete diffusion language models have emerged as a competitive alternative to auto-regressive language models, but training them efficiently under limited parameter and memory budgets remains challenging. Modern architectures are…

In this paper, we study multiple problems from sponsored product optimization in ad system, including position-based de-biasing, click-conversion multi-task learning, and calibration on predicted click-through-rate (pCTR). We propose a…

Most work in the deep learning systems community has focused on faster inference, but arriving at a trained model requires lengthy experiments. Accelerating training lets developers iterate faster and come up with better models. DNN…

This paper proposes a method to accelerate the training process of a general fuzzy min-max neural network. The purpose is to reduce the unsuitable hyperboxes selected as the potential candidates of the expansion step of existing hyperboxes…

Deep learning applications are computation-intensive and often employ GPU as the underlying computing devices. Deep learning frameworks provide powerful programming interfaces, but the gap between source codes and practical GPU operations…

Despite the growing prevalence of black-box pre-trained models (PTMs) such as prediction API services, there remains a significant challenge in directly applying general models to real-world scenarios due to the data distribution gap.…

Click-Through Rate prediction (CTR) is a crucial task in recommender systems, and it gained considerable attention in the past few years. The primary purpose of recent research emphasizes obtaining meaningful and powerful representations…

We propose a soft gradient boosting framework for sequential regression that embeds a learnable linear feature transform within the boosting procedure. At each boosting iteration, we train a soft decision tree and learn a linear input…

A key performance bottleneck when training graph neural network (GNN) models on large, real-world graphs is loading node features onto a GPU. Due to limited GPU memory, expensive data movement is necessary to facilitate the storage of these…

Feature selection aims to identify the optimal feature subset for enhancing downstream models. Effective feature selection can remove redundant features, save computational resources, accelerate the model learning process, and improve the…

Learning embedding table plays a fundamental role in Click-through rate(CTR) prediction from the view of the model performance and memory usage. The embedding table is a two-dimensional tensor, with its axes indicating the number of feature…

Feature engineering has been the key to the success of many prediction models. However, the process is non-trivial and often requires manual feature engineering or exhaustive searching. DNNs are able to automatically learn feature…

Integrating machine learning into the internals of database management systems requires significant feature engineering, a human effort-intensive process to determine the best way to represent the pieces of information that are relevant to…

Local learning offers an alternative to traditional end-to-end back-propagation in deep neural networks, significantly reducing GPU memory consumption. Although it has shown promise in image classification tasks, its extension to other…

Large embedding tables are indispensable in modern recommendation systems, thanks to their ability to effectively capture and memorize intricate details of interactions among diverse entities. As we explore integrating large embedding…

Although tremendous strides have been made in face detection, one of the remaining open challenges is to achieve real-time speed on the CPU as well as maintain high performance, since effective models for face detection tend to be…

Click-Through Rate (CTR) prediction is essential in online advertising, where semantic information plays a pivotal role in shaping user decisions and enhancing CTR effectiveness. Capturing and modeling deep semantic information, such as a…

Despite the high computational throughput of GPUs, limited memory capacity and bandwidth-limited CPU-GPU communication via PCIe links remain significant bottlenecks for accelerating large-scale data analytics workloads. This paper…

Training large language models (LLMs) efficiently requires a deep understanding of how modern GPU systems behave under real-world distributed training workloads. While prior work has focused primarily on kernel-level performance or…

Extracting and using class-discriminative features is critical for fine-grained recognition. Existing works have demonstrated the possibility of applying deep CNNs to exploit features that distinguish similar classes. However, CNNs suffer…