Heterogeneous Input

Heterogeneous input, encompassing data with varying dimensions, modalities, and feature sets, presents a significant challenge across diverse scientific domains. Current research focuses on developing robust methods to integrate and effectively utilize such data, employing techniques like multi-fidelity modeling, deep multimodal fusion with projective networks, and specialized neural network architectures designed for variable feature spaces. These advancements are crucial for improving the accuracy and efficiency of models in applications ranging from medical image analysis and materials science to complex networked systems and energy optimization, where data often originates from multiple, disparate sources.

Papers

March 19, 2024

Multi-fidelity surrogate with heterogeneous input spaces for modeling melt pools in laser-directed energy deposition
Nandana Menon, Amrita Basak
Multi Fidelity Thermal Simulation Heterogeneous Input Energy Deposition Melt Pool Multi Fidelity Gaussian Process

February 2, 2024

Deep Multimodal Fusion of Data with Heterogeneous Dimensionality via Projective Networks
José Morano, Guilherme Aresta, Christoph Grechenig, Ursula Schmidt-Erfurth, Hrvoje Bogunović
Raw Data Multimodal Data Multimodal Fusion Retinal Imaging Multi Modality Imaging Spatial Transformer Network Heterogeneous Input Retinal Blood Vessel Segmentation

December 21, 2023

HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces
Jiaxin Pan, Mojtaba Nayyeri, Yinan Li, Steffen Staab
Attention Mechanism Temporal Information Temporal Knowledge Graph Temporal Pattern Heterogeneous Input Temporal Fact

November 9, 2023

Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces
Tomoharu Iwata, Atsutoshi Kumagai
Semi Supervised Learning Meta Learning New Task Heterogeneous Input Semi Supervised Meta

November 6, 2023

FATE: Feature-Agnostic Transformer-based Encoder for learning generalized embedding spaces in flow cytometry data
Lisa Weijler, Florian Kowarsch, Michael Reiter, Pedro Hermosilla, Margarita Maurer-Granofszky, Michael Dworzak
Classification Task Mixed Space Heterogeneous Input Flow Cytometry Feature Encoder Modality Agnostic Transformer Encoder

October 29, 2023

D2NO: Efficient Handling of Heterogeneous Input Function Spaces with Distributed Deep Neural Operators
Zecheng Zhang, Christian Moya, Lu Lu, Guang Lin, Hayden Schaeffer
High Efficiency Neural Operator Universal Approximators Deep Neural Operator Heterogeneous Input Discretization Invariant

September 23, 2023

Heterogeneous Feature Representation for Digital Twin-Oriented Complex Networked Systems
Jiaqi Wen, Bogdan Gabrys, Katarzyna Musial
Digital Twin Complex Network Network Structure Heterogeneous Input

September 5, 2023

Linear Regression using Heterogeneous Data Batches
Ayush Jain, Rajat Sen, Weihao Kong, Abhimanyu Das, Alon Orlitsky
Linear Regression Mini Batch Gradient Based Algorithm Input Distribution Heterogeneous Input Vector Regression

July 26, 2023

Heterogeneous Embodied Multi-Agent Collaboration
Xinzhu Liu, Di Guo, Huaping Liu
Multi Agent Collaboration Heterogeneous Agent Multi Agent Task Heterogeneous Input

April 7, 2023

Supervised Contrastive Learning with Heterogeneous Similarity for Distribution Shifts
Takuro Kutsuna
Contrastive Learning Contrastive Loss Distribution Shift Supervised Contrastive Learning Heterogeneous Input

February 14, 2023

Joint Probability Trees
Daniel Nyga, Mareike Picklum, Tom Schierenbeck, Michael Beetz
Decision Tree Probabilistic Graphical Model Joint Distribution Posterior Probability Heterogeneous Input

January 26, 2023

Personalised Federated Learning On Heterogeneous Feature Spaces
Alain Rakotomamonjy, Maxime Vono, Hamlet Jesse Medina Ruiz, Liva Ralaivola
Federated Learning Representation Space Distribution Alignment Heterogeneous Input Heterogeneous Representation

April 7, 2022

Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models
Sibo Cheng, Jianhua Chen, Charitos Anastasiou, Panagiota Angeli, Omar K. Matar, Yi-Ke Guo, Christopher C. Pain, Rossella Arcucci
Data Assimilation Reduced Order Heterogeneous Input Latent Assimilation Machine Learning Surrogate

March 4, 2022

Continual Horizontal Federated Learning for Heterogeneous Data
Junki Mori, Isamu Teranishi, Ryo Furukawa
Machine Learning Continual Learning Heterogeneous Data Local Learning Heterogeneous Input Horizontal Federated Learning

February 18, 2022

Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
Tianyu Zhao, Cheng Yang, Yibo Li, Quan Gan, Zhenyi Wang, Fengqi Liang, Huan Zhao, Yingxia Shao, Xiao Wang, Chuan Shi
Long Form Novel Heterogeneous Graph Neural Network Heterogeneous Input

February 4, 2022

Distribution Embedding Networks for Generalization from a Diverse Set of Classification Tasks
Lang Liu, Mahdi Milani Fard, Sen Zhao
Strong Generalization Network Programming Classification Task Diverse Set Product Distribution Unseen Task Heterogeneous Input

November 4, 2021

Multi-Objective Constrained Optimization for Energy Applications via Tree Ensembles
Alexander Thebelt, Calvin Tsay, Robert M. Lee, Nathan Sudermann-Merx, David Walz, Tom Tranter, Ruth Misener
Energy Management Tree Ensemble Energy System Heterogeneous Input Data Driven Strategy

Heterogeneous Input

Papers

Multi-fidelity surrogate with heterogeneous input spaces for modeling melt pools in laser-directed energy deposition

Deep Multimodal Fusion of Data with Heterogeneous Dimensionality via Projective Networks

HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces

Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces

FATE: Feature-Agnostic Transformer-based Encoder for learning generalized embedding spaces in flow cytometry data

D2NO: Efficient Handling of Heterogeneous Input Function Spaces with Distributed Deep Neural Operators

Heterogeneous Feature Representation for Digital Twin-Oriented Complex Networked Systems

Linear Regression using Heterogeneous Data Batches

Heterogeneous Embodied Multi-Agent Collaboration

Supervised Contrastive Learning with Heterogeneous Similarity for Distribution Shifts

Joint Probability Trees

Personalised Federated Learning On Heterogeneous Feature Spaces

Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models

Continual Horizontal Federated Learning for Heterogeneous Data

Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network

Distribution Embedding Networks for Generalization from a Diverse Set of Classification Tasks

Multi-Objective Constrained Optimization for Energy Applications via Tree Ensembles