Global Deep

Global deep learning research focuses on developing and improving models that can effectively learn from and integrate vast, distributed datasets while addressing challenges like catastrophic forgetting and resource limitations. Current efforts concentrate on architectures such as graph neural networks, transformers, and convolutional neural networks, often incorporating techniques like federated learning, incremental learning, and local-global hybrid approaches to enhance efficiency and privacy. This field is significant for its potential to advance various applications, including healthcare (e.g., personalized medicine, neuroimaging analysis), autonomous driving (e.g., map creation), and environmental monitoring (e.g., remote sensing), by enabling the analysis of complex, large-scale data that would be otherwise intractable.

Papers

November 7, 2024

From Electrode to Global Brain: Integrating Multi- and Cross-Scale Brain Connections and Interactions Under Cross-Subject and Within-Subject Scenarios
Chen Zhige, Qin Chengxuan
Multi Scale Brain Function New Connection Electrode Array Motor Imagery Classification Global Deep

October 30, 2024

Domain-decomposed image classification algorithms using linear discriminant analysis and convolutional neural networks
Axel Klawonn, Martin Lanser, Janine Weber
Convolutional Neural Network Image Classification CNN Model Discriminant Analysis Global Deep

July 23, 2024

Local vs Global continual learning
Giulia Lanzillotta, Sidak Pal Singh, Benjamin F. Grewe, Thomas Hofmann
Continual LEArning Continual Learning Continual Learning Algorithm Global Deep Multi Task Loss

June 7, 2024

Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
Yibo Yang, Xiaojie Li, Motasem Alfarra, Hasan Hammoud, Adel Bibi, Philip Torr, Bernard Ghanem
Dynamic ModulE Local Learning Local Gradient Gradient Correction Global Deep

June 3, 2024

iKAN: Global Incremental Learning with KAN for Human Activity Recognition Across Heterogeneous Datasets
Mengxi Liu, Sizhen Bian, Bo Zhou, Paul Lukowicz
Incremental Learning Activity Recognition Kolmogorov Arnold Network Wearable Sensor Heterogeneous Datasets Global Deep

April 8, 2024

LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updating
Yufeng Yue, Yinan Deng, Jiahui Wang, Yi Yang
Signed Distance Field Fusion Feature Global Deep Local Update Implicit Reconstruction

February 14, 2024

CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding
Qiongyi Zhou, Changde Du, Shengpei Wang, Huiguang He
Image Decoder Global Deep Neural Information CLIP TD Outperforms

January 6, 2024

Multimodal Informative ViT: Information Aggregation and Distribution for Hyperspectral and LiDAR Classification
Jiaqing Zhang, Jie Lei, Weiying Xie, Geng Yang, Daixun Li, Yunsong Li
Hyperspectral Image Multimodal Phenomenon Multimodal Dataset Modal Embeddings Global Deep Land Cover Classification Information Aggregation

October 15, 2023

FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategy
Ziru Niu, Hai Dong, A. Kai Qin, Tao Gu
Deep Learning Federated Learning Early Stopping Communication Cost Global Deep

September 22, 2023

Forecasting Response to Treatment with Global Deep Learning and Patient-Specific Pharmacokinetic Priors
Willa Potosnak, Cristian Challu, Kin G. Olivares, Artur Dubrawski
Deep Learning Model Patient Specific Accurate Treatment Glucose Prediction Global Deep Pharmacokinetic Parameter Response Prediction

June 11, 2023

Local-to-global Perspectives on Graph Neural Networks
Chen Cai
Graph Neural Network Graph Transformer Message Passing Neural Network Global Deep Invariant Graph Network

May 9, 2023

Turning Privacy-preserving Mechanisms against Federated Learning
Marco Arazzi, Mauro Conti, Antonino Nocera, Stjepan Picek
Graph Neural Network Privacy Preserving Functional Mechanism Differential Privacy Mechanism Global Deep

April 28, 2023

Hierarchical and Decentralised Federated Learning
Omer Rana, Theodoros Spyridopoulos, Nathaniel Hudson, Matt Baughman, Kyle Chard, Ian Foster, Aftab Khan
Machine Learning Model Decentralized Federated Learning Model Aggregation Hierarchical Federated Learning Global Deep

April 20, 2023

Using Z3 for Formal Modeling and Verification of FNN Global Robustness
Yihao Zhang, Zeming Wei, Xiyue Zhang, Meng Sun
Adversarial Robustness Verification Task Formal Model Global Deep Global Robustness DNN Robustness Adversarial Region

April 17, 2023

Neural Map Prior for Autonomous Driving
Xuan Xiong, Yicheng Liu, Tianyuan Yuan, Yue Wang, Yilun Wang, Hang Zhao
Autonomous Driving Semantic Map Map Prior MAP Estimation Global Deep Map Prediction

May 18, 2022

Federated learning: Applications, challenges and future directions
Subrato Bharati, M. Rubaiyat Hossain Mondal, Prajoy Podder, V. B. Surya Prasath
Technical Challenge Financial Application Differential Privacy Stochastic Gradient Descent Future Direction Homomorphic Encryption Global Deep

May 11, 2022

Secure & Private Federated Neuroimaging
Dimitris Stripelis, Umang Gupta, Hamza Saleem, Nikhil Dhinagar, Tanmay Ghai, Rafael Chrysovalantis Anastasiou, Armaghan Asghar, Greg Ver Steeg, Srivatsan Ravi, Muhammad Naveed, Paul M. Thompson, Jose Luis Ambite
Private Data Secure Approach Global Deep Federated Learning Architecture

March 21, 2022

Multi-modal learning for predicting the genotype of glioma
Yiran Wei, Xi Chen, Lei Zhu, Lipei Zhang, Carola-Bibiane Schönlieb, Stephen J. Price, Chao Li
Multi Modal Global Deep Isocitrate Dehydrogenase Mutation Diffuse Glioma Tumor Shape Genotype Phenotype Glioma Subtype Classification

November 5, 2021