Related papers: NNTile: a machine learning framework capable of tr…

Large language models (LLMs) require vast amounts of GPU compute to train, but limited availability and high costs of GPUs make homogeneous clusters impractical for many organizations. Instead, assembling heterogeneous clusters by pooling…

Multi-Task Learning (MTL) enables a single model to learn multiple tasks simultaneously, leveraging knowledge transfer among tasks for enhanced generalization, and has been widely applied across various domains. However, task imbalance…

In Neural Machine Translation (NMT) the usage of subwords and characters as source and target units offers a simple and flexible solution for translation of rare and unseen words. However, selecting the optimal subword segmentation involves…

ANNdotNET is an open source project for deep learning written in C# with ability to create, train, evaluate and export deep learning models. The project consists of the Graphical User Interface module capable to visually prepare data, fine…

With the increased penetration and proliferation of Internet of Things (IoT) devices, there is a growing trend towards distributing the power of deep learning (DL) across edge devices rather than centralizing it in the cloud. This…

Graph neural networks (GNNs) have been demonstrated as a powerful tool for analyzing non-Euclidean graph data. However, the lack of efficient distributed graph learning systems severely hinders applications of GNNs, especially when graphs…

In this paper, we propose a novel multi-task learning (MTL) framework, called Self-Paced Multi-Task Learning (SPMTL). Different from previous works treating all tasks and instances equally when training, SPMTL attempts to jointly learn the…

Neural machine translation (NMT) becomes a new state-of-the-art and achieves promising translation results using a simple encoder-decoder neural network. This neural network is trained once on the parallel corpus and the fixed network is…

The training process of Deep Neural Network (DNN) is compute-intensive, often taking days to weeks to train a DNN model. Therefore, parallel execution of DNN training on GPUs is a widely adopted approach to speed up the process nowadays.…

Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of…

Neural machine translation (NMT) has been accelerated by deep learning neural networks over statistical-based approaches, due to the plethora and programmability of commodity heterogeneous computing architectures such as FPGAs and GPUs and…

Training deep learning (DL) models across Graphics Processing Unit (GPU) clusters is technically challenging. One aspect is that users have to compose command lines to adapt to the heterogeneous launchers, schedulers, affinity options, DL…

Network embedding (NE) can generate succinct node representations for massive-scale networks and enable direct applications of common machine learning methods to the network structure. Various NE algorithms have been proposed and used in a…

Modern machine learning models are typically trained using Stochastic Gradient Descent (SGD) on massively parallel computing resources such as GPUs. Increasing mini-batch size is a simple and direct way to utilize the parallel computing…

Empirical natural language processing (NLP) systems in application domains (e.g., healthcare, finance, education) involve interoperation among multiple components, ranging from data ingestion, human annotation, to text retrieval, analysis,…

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been…

As a language model that integrates traditional symbolic operations and flexible neural representations, recurrent neural network grammars (RNNGs) have attracted great attention from both scientific and engineering perspectives. However,…

We consider the problem of making efficient use of heterogeneous training data in neural machine translation (NMT). Specifically, given a training dataset with a sentence-level feature such as noise, we seek an optimal curriculum, or order…

Long training times for high-accuracy deep neural networks (DNNs) impede research into new DNN architectures and slow the development of high-accuracy DNNs. In this paper we present FireCaffe, which successfully scales deep neural network…

Current approaches to automated code generation often rely on monolithic models that lack real-time adaptability and scalability. This limitation is particularly evident in complex programming tasks that require dynamic adjustment and…