Heterogeneous Datasets

Heterogeneous datasets, encompassing diverse data types and distributions, pose significant challenges for machine learning, hindering model training and generalization. Current research focuses on developing robust algorithms and model architectures, such as federated learning frameworks (e.g., UniFed, FedCompass), biclustering techniques (e.g., HBIC), and ensemble methods, to effectively analyze these complex datasets. This work is crucial for advancing various fields, including personalized medicine, IoT cybersecurity, and crop yield prediction, where integrating disparate data sources is essential for improved accuracy and actionable insights.

Papers

March 19, 2023

Label Name is Mantra: Unifying Point Cloud Segmentation across Heterogeneous Datasets
Yixun Liang, Hao He, Shishi Xiao, Hao Lu, Yingcong Chen
Point Cloud Point Cloud Segmentation 3D Space Heterogeneous Datasets Continuous Latent Space

January 28, 2023

Heterogeneous Datasets for Federated Survival Analysis Simulation
Alberto Archetti, Eugenio Lomurno, Francesco Lattari, André Martin, Matteo Matteucci
Survival Model Heterogeneous Datasets Federated Survival

January 18, 2023

Training Semantic Segmentation on Heterogeneous Datasets
Panagiotis Meletis, Gijs Dubbelman
Semantic Segmentation Label Space Heterogeneous Datasets Single Learning Heterogeneous Training

November 17, 2022

FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data
Ming Yang, Yanhan Wang, Xin Wang, Zhenyong Zhang, Xiaoming Wu, Peng Cheng
Contrastive Learning Raw Data Siamese Network Data Heterogeneity Heterogeneous Datasets Federated Contrastive Learning

September 18, 2022

Hierarchical fuzzy neural networks with privacy preservation for heterogeneous big data
Leijie Zhang, Ye Shi, Yu-Cheng Chang, Chin-Teng Lin
Neural Network Privacy Preserving Sensitive Data Big Data Privacy Preservation Heterogeneous Datasets

July 22, 2022

AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets
Yuqing Zhao, Divya Saxena, Jiannong Cao
Continual LEArning Heterogeneous Datasets Sequential Observation Adaptive Continual Learning Agnostic Continual Learning

July 17, 2022

Personalized PCA: Decoupling Shared and Unique Features
Naichen Shi, Raed Al Kontar
Video Segmentation PCa Detection Sharing Matter Heterogeneous Datasets Unique Feature Personalized Face Recognition

June 5, 2022

OntoMerger: An Ontology Integration Library for Deduplicating and Connecting Knowledge Graph Nodes
David Geleta, Andriy Nikolov, Mark ODonoghue, Benedek Rozemberczki, Anna Gogleva, Valentina Tamma, Terry R. Payne
Knowledge Graph Top Level Ontology Heterogeneous Datasets Data Deduplication Ontology Quality

June 4, 2022

Interpretable Models Capable of Handling Systematic Missingness in Imbalanced Classes and Heterogeneous Datasets
Sreejita Ghosh, Elizabeth S. Baranowski, Michael Biehl, Wiebke Arlt, Peter Tino, Kerstin Bunte
Class Imbalance Interpretable Model Patient Data Medical Datasets Heterogeneous Datasets Missingness Pattern

May 2, 2022

FedDKD: Federated Learning with Decentralized Knowledge Distillation
Xinjia Li, Boyu Chen, Wenlian Lu
Knowledge Distillation Heterogeneous Datasets Neural Mapping Decentralized Knowledge Distillation

Heterogeneous Datasets

Papers

Label Name is Mantra: Unifying Point Cloud Segmentation across Heterogeneous Datasets

Heterogeneous Datasets for Federated Survival Analysis Simulation

Training Semantic Segmentation on Heterogeneous Datasets

FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data

Hierarchical fuzzy neural networks with privacy preservation for heterogeneous big data

AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets

Personalized PCA: Decoupling Shared and Unique Features

OntoMerger: An Ontology Integration Library for Deduplicating and Connecting Knowledge Graph Nodes

Interpretable Models Capable of Handling Systematic Missingness in Imbalanced Classes and Heterogeneous Datasets

FedDKD: Federated Learning with Decentralized Knowledge Distillation