DL Model

Deep learning (DL) models are computational tools used to solve complex problems by learning patterns from data, with primary objectives focused on improving accuracy, efficiency, and explainability. Current research emphasizes optimizing model training, particularly for large-scale applications like recommendation systems, by addressing communication bottlenecks and improving data pipeline efficiency through techniques like lossy compression and reinforcement learning-based resource allocation. These advancements are significant for various fields, enabling improvements in predictive maintenance, financial modeling, and scientific data analysis while also addressing challenges related to data privacy and energy consumption during model training.

Papers

July 5, 2024

Accelerating Communication in Deep Learning Recommendation Model Training with Dual-Level Adaptive Lossy Compression
Hao Feng, Boyuan Zhang, Fanjiang Ye, Min Si, Ching-Hsiang Chu, Jiannan Tian, Chunxing Yin, Summer Deng, Yuchen Hao, Pavan Balaji, Tong Geng, Dingwen Tao
Timely Communication Efficient Training Deep Learning Recommendation Model Error Bounded Lossy DL Model

June 19, 2024

State-of-the-Art Review: The Use of Digital Twins to Support Artificial Intelligence-Guided Predictive Maintenance
Sizhe Ma, Katherine A. Flanigan, Mario Bergés
Digital Twin Greater Public Use Synthetic to Real Decomposed Automation Correction DL Model

April 12, 2024

Differentially Private Log-Location-Scale Regression Using Functional Mechanism
Jiewen Sheng, Xiaolei Fang
Differential Privacy Functional Mechanism Private Estimation Private Linear Regression DL Model \Ell_p$ Regression

March 10, 2024

How much data do you need? Part 2: Predicting DL class specific training dataset sizes
Thomas Mühlenstädt, Jelena Frtunikj
Different PaRT MNIST Dataset Linear Model Dataset Size Much Data DL Model Training Dataset Size

August 22, 2023

Automatic Task Parallelization of Dataflow Graphs in ML/DL models
Srinjoy Das, Lawrence Rauchwerger
Machine Learning Pytorch Model Graph Machine Learning Pipeline Parallelism 3D Parallelism Dataflow Graph DL Model

August 13, 2023

InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Models
Kabir Nagrecha, Lingyi Liu, Pablo Delgado, Prasanna Padmanabhan
Efficient Pipeline Training Bottleneck DL Model Deep Recommendation

April 12, 2023

Identifying Trades Using Technical Analysis and ML/DL Models
Aayush Shah, Mann Doshi, Meet Parekh, Nirmit Deliwala, Prof. Pramila M. Chawan
Deep Learning Machine Learning Stock Market Stock Market Prediction Stock Price Post Trade Allocation Technical Indicator DL Model

February 5, 2023

Explainable Machine Learning: The Importance of a System-Centric Perspective
Manish Narwaria
Machine Learning Importance Aware Explainable Machine Learning Implicit Model DL Model

February 2, 2023

Energy Efficiency of Training Neural Network Architectures: An Empirical Study
Yinlena Xu, Silverio Martínez-Fernández, Matias Martinez, Xavier Franch
Deep Learning Model Deep Convolutional Neural Network Empirical Study Neural Architecture Energy Efficiency Carbon Footprint DL Model

April 8, 2022

LaF: Labeling-Free Model Selection for Automated Deep Neural Network Reusing
Qiang Hu, Yuejun Guo, Maxime Cordy, Xiaofei Xie, Mike Papadakis, Yves Le Traon
Deep Learning Model Selection DNN Model Label Free Large Pre Trained Automated Deep Learning DL Model