Deep Neural Network Ensemble

Deep neural network ensembles combine the predictions of multiple individual DNNs to improve accuracy, robustness, and uncertainty quantification compared to single models. Current research focuses on developing efficient ensemble methods, particularly for resource-constrained settings like edge devices and semi-supervised learning scenarios, exploring diverse ensemble architectures (e.g., heterogeneous models addressing different tasks), and leveraging techniques like knowledge distillation and Bayesian methods to enhance performance and reduce complexity. These advancements are significant for various applications, including improving the reliability of predictions in critical domains like healthcare and mitigating the vulnerability of DNNs to adversarial attacks.

Papers

November 4, 2024

Stein Variational Newton Neural Network Ensembles
Klemens Flöge, Mohammed Abdul Moeed, Vincent Fortuin
Hessian Matrix Deep Ensemble Approximate Bayesian Inference Stein Variational Gradient Descent Deep Neural Network Ensemble

May 6, 2024

E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification
Xin Zhang, Daochen Zha, Qiaoyu Tan
Ensemble Learning GNN Model Semi Supervised Classification Ensemble Neural Network Deep Neural Network Ensemble

October 3, 2023

Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness
Yanzhao Wu, Ka-Ho Chow, Wenqi Wei, Ling Liu
Ensemble Diversity Robust Ensemble Heterogeneous Ensemble Model Heterogeneity Deep Neural Network Ensemble

September 6, 2023

Ensemble DNN for Age-of-Information Minimization in UAV-assisted Networks
Mouhamed Naby Ndiaye, El Houcine Bergou, Hajar El Hammouti
Deep Neural Network Age of Information Deep Neural Network Ensemble Ensemble Deep UAV Assisted

July 11, 2023

Predicting small molecules solubilities on endpoint devices using deep ensemble neural networks
Mayk Caldas Ramos, Andrew D. White
Molecular Property Prediction First Principle Deep Neural Network Ensemble Endpoint Detection Solubility Prediction

May 16, 2023

Privacy-Preserving Ensemble Infused Enhanced Deep Neural Network Framework for Edge Cloud Convergence
Veronika Stephanie, Ibrahim Khalil, Mohammad Saidur Rahman, Mohammed Atiquzzaman
Deep Neural Network Ensemble Learning Privacy Preserving Sensitive Data Edge Cloud Deep Neural Network Ensemble

March 1, 2023

FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling
Wei-Yin Ko, Daniel D'souza, Karina Nguyen, Randall Balestriero, Sara Hooker
Procedural Fairness Diverse Ensemble Model Ensembling Multiple Deep Neural Network Heterogeneous Ensemble Deep Neural Network Ensemble

February 23, 2023

Practical Knowledge Distillation: Using DNNs to Beat DNNs
Chung-Wei Lee, Pavlos Athanasios Apostolopulos, Igor L. Markov
Knowledge Distillation DNN Framework Gradient Boosting Model Distillation Deep Neural Network Performance Deep Neural Network Ensemble

February 1, 2023

DANES: Deep Neural Network Ensemble Architecture for Social and Textual Context-aware Fake News Detection
Ciprian-Octavian Truică, Elena-Simona Apostol, Panagiotis Karras
Textual Feature Deep Neural Network Ensemble

June 1, 2022

Sequential Bayesian Neural Subnetwork Ensembles
Sanket Jantre, Sandeep Madireddy, Shrijita Bhattacharya, Tapabrata Maiti, Prasanna Balaprakash
Model Ensembling Sparse Subnetworks Bayesian Ensemble Deep Neural Network Ensemble

February 8, 2022

Verification-Aided Deep Ensemble Selection
Guy Amir, Tom Zelazny, Guy Katz, Michael Schapira
Deep Neural Network Ensemble Classifier DNN Verification Deep Neural Network Ensemble DNN Verifier