Heterogeneous Feature

Heterogeneous features, encompassing diverse data types and distributions, pose significant challenges in machine learning. Current research focuses on developing methods to effectively handle this heterogeneity, including techniques like adaptive batch normalization to optimize model training, novel feature selection algorithms to reduce computational complexity and improve efficiency, and specialized model architectures (e.g., mixtures of experts, decoupled feature extractors) to better leverage diverse information sources. Addressing heterogeneous features is crucial for improving the accuracy and efficiency of machine learning models across various applications, from autonomous driving and medical image analysis to federated learning and tensor program generation.

Papers

September 9, 2024

Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection
Huang-Yu Chen, Jia-Fong Yeh, Jia-Wei Liao, Pin-Hsuan Peng, Winston H. Hsu
Active Learning 3D Object Detection Feature Diversity Distribution Discrepancy Heterogeneous Feature

May 31, 2024

Superfast Selection for Decision Tree Algorithms
Huaduo Wang, Gopal Gupta
Feature Selection Decision Tree Dynamic Selection Heterogeneous Feature

December 19, 2023

Generator Assisted Mixture of Experts For Feature Acquisition in Batch
Vedang Asgaonkar, Aditya Jain, Abir De
Expert Knowledge Batch Greenkhorn Acquisition Trajectory Feature Acquisition Critical Mixture Ratio Heterogeneous Feature

November 30, 2023

FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learning
Lingzhi Gao, Zexi Li, Yang Lu, Chao Wu
Personalized Knowledge Personalization System Heterogeneous Feature

July 6, 2023

Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles
Benjamin S. Ruben, Cengiz Pehlevan
Linear Classifier Learning Curve Heterogeneous Feature Ridge Ensemble

April 11, 2023

Transfer Learning Across Heterogeneous Features For Efficient Tensor Program Generation
Gaurav Verma, Siddhisanket Raskar, Zhen Xie, Abid M Malik, Murali Emani, Barbara Chapman
Transfer Learning Tensor Program Joint Neural Heterogeneous Feature

November 3, 2022

Adaptive Batch Normalization for Training Data with Heterogeneous Features
Wael Alsobhi, Tarik Alafif, Alaa Abdel-Hakim, Weiwei Zong
Training Data Batch Normalization Normalization Dictionary Large Batch Threshold Based Heterogeneous Feature

May 18, 2022

Scalable Multi-view Clustering with Graph Filtering
Liang Liu, Peng Chen, Guangchun Luo, Zhao Kang, Yonggang Luo, Sanchu Han
Multi View Multi View Clustering Graph Filter Topological Information Heterogeneous Feature

December 20, 2021

HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images
Meirui Jiang, Zirui Wang, Qi Dou
Medical Image Medical Image Classification Drift Detection Local Model Heterogeneous Feature Unified Image Heterogeneous Medical Image