Deep Learning Framework

Deep learning frameworks are computational tools designed to build and train artificial neural networks for diverse applications. Current research emphasizes developing frameworks tailored to specific data types (e.g., tabular, temporal, image, audio) and tasks (e.g., classification, regression, anomaly detection), often incorporating architectures like convolutional neural networks, recurrent neural networks, transformers, and graph neural networks. These frameworks are significantly impacting various fields, from improving medical image analysis and accelerating scientific simulations to optimizing industrial processes and enhancing personalized advertising strategies.

Papers

April 18, 2023

A Deep Learning Framework for Traffic Data Imputation Considering Spatiotemporal Dependencies
Li Jiang, Ting Zhang, Qiruyi Zuo, Chenyu Tian, George P. Chan, Wai Kin, Chan
Time Series Temporal Dependency Deep Learning Framework Spatio tempOral Spatiotemporal Imputation Traffic Data Imputation

April 5, 2023

Explaining Multimodal Data Fusion: Occlusion Analysis for Wilderness Mapping
Burak Ekim, Michael Schmitt
Deep Learning Framework Different Modality Multimodal Data Fusion Multi Modal Input Virtual Occlusion Wilderness Search

March 16, 2023

cito: An R package for training neural networks using torch
Christian Amesoeder, Florian Hartig, Maximilian Pichler
Neural Network Deep Neural Network Deep Learning Framework R Package Biodiversity Monitoring

March 11, 2023

A Hybrid Tensor-Expert-Data Parallelism Approach to Optimize Mixture-of-Experts Training
Siddharth Singh, Olatunji Ruwase, Ammar Ahmad Awan, Samyam Rajbhandari, Yuxiong He, Abhinav Bhatele
Training Data Mixture of Expert Deep Learning Framework Expert Parallelism Tensor Parallelism DeepSpeed Data Efficiency DeepSpeed Ulysses

March 8, 2023

RAF: Holistic Compilation for Deep Learning Model Training
Cody Hao Yu, Haozheng Fan, Guangtai Huang, Zhen Jia, Yizhi Liu, Jie Wang, Zach Zheng, Yuan Zhou, Haichen Shen, Junru Shao, Mu Li, Yida Wang
Deep Learning Framework Training Deep Tensor Compiler Compiler Optimization Planning Based Compilation Deep Learning Compiler

March 7, 2023

ADELT: Transpilation Between Deep Learning Frameworks
Linyuan Gong, Jiayi Wang, Alvin Cheung
Pytorch Model Deep Learning Framework Multi Modal Skeleton Input

February 24, 2023

DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining
Lin Zhang, Shaohuai Shi, Xiaowen Chu, Wei Wang, Bo Li, Chengjian Liu
Deep Learning Deep Learning Framework Feed Forward Multi Hop All Reduce

February 22, 2023

February 19, 2023

February 13, 2023

February 2, 2023

Geometric Deep Learning for Autonomous Driving: Unlocking the Power of Graph Neural Networks With CommonRoad-Geometric
Eivind Meyer, Maurice Brenner, Bowen Zhang, Max Schickert, Bilal Musani, Matthias Althoff
Graph Neural Network Autonomous Driving Trajectory Prediction Real Power Heterogeneous Graph Deep Learning Framework Geometric Deep Learning Graph Datasets

January 30, 2023

FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscation
Hanlin Gu, Jiahuan Luo, Yan Kang, Lixin Fan, Qiang Yang
Privacy Preserving Deep Learning Framework Vertical Federated Learning Obfuscation Technique Private Feature

January 17, 2023

Face Inverse Rendering via Hierarchical Decoupling
Meng Wang, Xiaojie Guo, Wenjing Dai, Jiawan Zhang
Deep Learning Framework Inverse Rendering Multi Agent Decoupling Coefficient

January 12, 2023

A Novel Framework for Handling Sparse Data in Traffic Forecast
Nikolaos Zygouras, Dimitrios Gunopulos
Deep Learning Framework Traffic Prediction Traffic Data Novel Framework Sparse Data Future Traffic Real Time Traffic

December 28, 2022

CT-LungNet: A Deep Learning Framework for Precise Lung Tissue Segmentation in 3D Thoracic CT Scans
Niloufar Delfan, Hamid Abrishami Moghaddam, Mohammadreza Modaresi, Kimia Afshari, Kasra Nezamabadi, Neda Pak, Omid Ghaemi, Mohamad Forouzanfar
Deep Learning Framework Lung Segmentation 3d Ct Chest CT Robust Segmentation Lung CT

November 28, 2022

An Empirical Study of Library Usage and Dependency in Deep Learning Frameworks
Mohamed Raed El aoun, Lionel Nganyewou Tidjon, Ben Rombaut, Foutse Khomh, Ahmed E. Hassan
Deep Learning Empirical Study Deep Learning Framework Easy to Use Library State of the Art Deep Deep Learning Library Dependency Aware Incident High Performance Library

November 15, 2022

ParticleGrid: Enabling Deep Learning using 3D Representation of Materials
Shehtab Zaman, Ethan Ferguson, Cecile Pereira, Denis Akhiyarov, Mauricio Araya-Polo, Kenneth Chiu
Deep Learning Deep Learning Framework 3d Representation Deep Learning Application Material Response Material Property Prediction Chemical Structure Material Generation

Deep Learning Framework

Papers

A Deep Learning Framework for Traffic Data Imputation Considering Spatiotemporal Dependencies

Explaining Multimodal Data Fusion: Occlusion Analysis for Wilderness Mapping

cito: An R package for training neural networks using torch

A Hybrid Tensor-Expert-Data Parallelism Approach to Optimize Mixture-of-Experts Training

RAF: Holistic Compilation for Deep Learning Model Training

ADELT: Transpilation Between Deep Learning Frameworks

DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining

Video-SwinUNet: Spatio-temporal Deep Learning Framework for VFSS Instance Segmentation

The DeepCAR Method: Forecasting Time-Series Data That Have Change Points

Physics-aware deep learning framework for linear elasticity

Wrapyfi: A Python Wrapper for Integrating Robots, Sensors, and Applications across Multiple Middleware

The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment

Generalizable End-to-End Deep Learning Frameworks for Real-Time Attitude Estimation Using 6DoF Inertial Measurement Units

Geometric Deep Learning for Autonomous Driving: Unlocking the Power of Graph Neural Networks With CommonRoad-Geometric

FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscation

Face Inverse Rendering via Hierarchical Decoupling

A Novel Framework for Handling Sparse Data in Traffic Forecast

CT-LungNet: A Deep Learning Framework for Precise Lung Tissue Segmentation in 3D Thoracic CT Scans

An Empirical Study of Library Usage and Dependency in Deep Learning Frameworks

ParticleGrid: Enabling Deep Learning using 3D Representation of Materials