Local Datasets

Local datasets are small, often project-specific datasets used to train machine learning models, addressing challenges posed by data scarcity, privacy concerns, or the need for tailored solutions. Current research focuses on techniques like federated learning, which allows collaborative model training without sharing raw data, and on developing algorithms to mitigate issues arising from data heterogeneity and limited sample sizes, including active sampling and self-distillation methods. This research is significant because it enables the development of effective machine learning models in diverse contexts, from personalized healthcare to infrastructure monitoring in resource-constrained settings, while addressing crucial privacy and efficiency considerations.

Papers

September 3, 2024

Personalized Federated Learning via Active Sampling
Alexander Jung, Yasmin SarcheshmehPour, Amirhossein Mohammadi
Personalized Federated Learning Data Generation Active Sampling Local Datasets

August 10, 2024

Advancing Pavement Distress Detection in Developing Countries: A Novel Deep Learning Approach with Locally-Collected Datasets
Blessing Agyei Kyem, Eugene Kofi Okrah Denteh, Joshua Kofi Asamoah, Kenneth Adomako Tutu, Armstrong Aboah
Deep Learning Local Datasets Pavement Distress Pavement Condition

July 3, 2024

Semantically Rich Local Dataset Generation for Explainable AI in Genomics
Pedro Barbosa, Rosina Savisaar, Alcides Fonseca
Explainable AI Genetic Programming RNA Sequence Local Datasets Interpretable Surrogate Model Syntactic Relation Sequence Relationship

February 19, 2024

Secure Federated Learning Across Heterogeneous Cloud and High-Performance Computing Resources -- A Case Study on Federated Fine-tuning of LLaMA 2
Zilinghan Li, Shilan He, Pranshu Chaturvedi, Volodymyr Kindratenko, Eliu A Huerta, Kibaek Kim, Ravi Madduri
Fine Tuning Federated Learning Heterogeneous Computing LLaMa LlamaCare Privacy Preserving Federated Learning Local Datasets

February 8, 2024

Asynchronous Diffusion Learning with Agent Subsampling and Local Updates
Elsa Rizk, Kun Yuan, Ali H. Sayed
Practical Algorithm Global Model Local Context Client Sampling Asynchronous Learning Local Datasets

July 24, 2023

Addressing the Impact of Localized Training Data in Graph Neural Networks
Akansha A
Graph Neural Network Global Impact Semi Supervised Graph Structured Data Semi Supervised Node Classification Graph Inference Local Datasets

July 13, 2023

Online Distributed Learning with Quantized Finite-Time Coordination
Nicola Bastianello, Apostolos I. Rikos, Karl H. Johansson
LeArning Abstract Gradient Descent Stochastic Gradient Online Service Learning Model Coordination Strategy Local Datasets

June 27, 2023

Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile
Tyler LeBlond, Joseph Munoz, Fred Lu, Maya Fuchs, Elliott Zaresky-Williams, Edward Raff, Brian Testa
Machine Learning Model Differential Privacy PRIvacy Leakage Privacy Budget Local Datasets Late Time Transition Dataset Level Privacy

May 31, 2023

Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning
M. Yashwanth, Gaurav Kumar Nayak, Arya Singh, Yogesh Simmhan, Anirban Chakraborty
Regularization Model Self Distillation Heterogeneous Federated Learning Local Datasets Client Drift

May 3, 2023

LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
Timothy Castiglia, Yi Zhou, Shiqiang Wang, Swanand Kadhe, Nathalie Baracaldo, Stacy Patterson
Feature Selection Vertical Federated Learning Local Feature Communication Efficient Local Datasets VFL Algorithm Feature Set

May 1, 2023

June 30, 2022

Learning Underrepresented Classes from Decentralized Partially Labeled Medical Images
Nanqing Dong, Michael Kampffmeyer, Irina Voiculescu
Self Supervised Learning Medical Image Multi Label Decentralized FL Underrepresented Group Local Datasets

June 2, 2022

Learning code summarization from a small and local dataset
Toufique Ahmed, Premkumar Devanbu
Foundation Model Software Engineering Code Summarization Local Datasets Training Point Subject Based Training

May 30, 2022

FedAUXfdp: Differentially Private One-Shot Federated Distillation
Haley Hoech, Roman Rischke, Karsten Müller, Wojciech Samek
Federated Learning Deep Network Federated Distillation Local Datasets FedCF Method

December 28, 2021

Robust Convergence in Federated Learning through Label-wise Clustering
Hunmin Lee, Yueyang Liu, Donghyun Kim, Yingshu Li
Heterogeneous Client Local Datasets Cluster Label