Related papers: Scalable Neural Data Server: A Data Recommender fo…

Transfer learning has proven to be a successful technique to train deep learning models in the domains where little training data is available. The dominant approach is to pretrain a model on a large generic dataset such as ImageNet and…

We present DS-Serve, a framework that transforms large-scale text datasets, comprising half a trillion tokens, into a high-performance neural retrieval system. DS-Serve offers both a web interface and API endpoints, achieving low latency…

Deep learning (DL) has achieved remarkable progress in the field of medical imaging. However, adapting DL models to medical tasks remains a significant challenge, primarily due to two key factors: (1) architecture selection, as different…

Neural personalized recommendation models are used across a wide variety of datacenter applications including search, social media, and entertainment. State-of-the-art models comprise large embedding tables that have billions of parameters…

The current success of deep neural networks (DNNs) in an increasingly broad range of tasks involving artificial intelligence strongly depends on the quality and quantity of labeled training data. In general, the scarcity of labeled data,…

To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems. Similarly, a machine learning model…

Most popular, modern network simulators, such as ns, are targeted towards simulating low-level protocol details. These existing simulators are not intended for simulating large distributed applications with many hosts and many concurrent…

In the era of data proliferation, efficiently sifting through vast information to extract meaningful insights has become increasingly crucial. This paper addresses the computational overhead and resource inefficiency prevalent in existing…

Self-supervised learning (SSL), especially contrastive methods, has raised attraction recently as it learns effective transferable representations without semantic annotations. A common practice for self-supervised pre-training is to use as…

Deep neural networks (DNNs) form the cornerstone of modern AI services, supporting a wide range of applications, including autonomous driving, chatbots, and recommendation systems. As models increase in size and complexity, DNN workloads…

Deep neural networks (DNN) has received increasing attention in machine learning applications in the last several years. Recently, a non-asymptotic error bound has been developed to measure the performance of the fully connected DNN…

Dense embedding models are commonly deployed in commercial search engines, wherein all the document vectors are pre-computed, and near-neighbor search (NNS) is performed with the query vector to find relevant documents. However, the…

Deep learning models require extensive architecture design exploration and hyperparameter optimization to perform well on a given task. The exploration of the model design space is often made by a human expert, and optimized using a…

The paradigm of training models on massive data without label through self-supervised learning (SSL) and finetuning on many downstream tasks has become a trend recently. However, due to the high training costs and the unconsciousness of…

Deep Neural Networks~(DNNs) have been widely deployed in software to address various tasks~(e.g., autonomous driving, medical diagnosis). However, they could also produce incorrect behaviors that result in financial losses and even threaten…

Semi-Supervised Learning (SSL) has become a preferred paradigm in many deep learning tasks, which reduces the need for human labor. Previous studies primarily focus on effectively utilising the labelled and unlabeled data to improve…

Training neural networks requires increasing amounts of memory. Parameter sharing can reduce memory and communication costs, but existing methods assume networks have many identical layers and utilize hand-crafted sharing strategies that…

Recent methods aim to merge neural networks (NNs) with identical architectures trained on different tasks into a single multi-task model. While most works focus on the simpler setup of merging NNs initialized from a common pre-trained…

Deep Learning (DL) models have achieved superior performance in many application domains, including vision, language, medical, commercial ads, entertainment, etc. With the fast development, both DL applications and the underlying serving…

Transfer learning has been developed to improve the performances of different but related tasks in machine learning. However, such processes become less efficient with the increase of the size of training data and the number of tasks.…