dorsal/arxiv
View SchemaMulti-task Modeling for Engineering Applications with Sparse Data
| Authors | Yigitcan Comlek, R. Murali Krishnan, Sandipp Krishnan Ravi, Amin Moghaddas, Rafael Giorjao, Michael Eff, Anirban Samaddar, Nesar S. Ramachandra, Sandeep Madireddy, Liping Wang |
|---|---|
| Categories | |
| ArXiv ID | 2601.05910vv1 |
| URL | https://arxiv.org/abs/2601.05910 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
Modern engineering and scientific workflows often require simultaneous predictions across related tasks and fidelity levels, where high-fidelity data is scarce and expensive, while low-fidelity data is more abundant. This paper introduces an Multi-Task Gaussian Processes (MTGP) framework tailored for engineering systems characterized by multi-source, multi-fidelity data, addressing challenges of data sparsity and varying task correlations. The proposed framework leverages inter-task relationships across outputs and fidelity levels to improve predictive performance and reduce computational costs. The framework is validated across three representative scenarios: Forrester function benchmark, 3D ellipsoidal void modeling, and friction-stir welding. By quantifying and leveraging inter-task relationships, the proposed MTGP framework offers a robust and scalable solution for predictive modeling in domains with significant computational and experimental costs, supporting informed decision-making and efficient resource utilization.
{
"annotation_id": "0e0d3483-a959-44cf-a0c5-9e587937ea1c",
"date_created": "2026-02-17T05:53:05.115000Z",
"date_modified": "2026-02-17T05:53:05.115000Z",
"file_hash": "2929c3e254093373d62b50a28ced1ef6170e386e8c62bd192bdebc255d080fae",
"private": false,
"record": {
"abstract": "Modern engineering and scientific workflows often require simultaneous predictions across related tasks and fidelity levels, where high-fidelity data is scarce and expensive, while low-fidelity data is more abundant. This paper introduces an Multi-Task Gaussian Processes (MTGP) framework tailored for engineering systems characterized by multi-source, multi-fidelity data, addressing challenges of data sparsity and varying task correlations. The proposed framework leverages inter-task relationships across outputs and fidelity levels to improve predictive performance and reduce computational costs. The framework is validated across three representative scenarios: Forrester function benchmark, 3D ellipsoidal void modeling, and friction-stir welding. By quantifying and leveraging inter-task relationships, the proposed MTGP framework offers a robust and scalable solution for predictive modeling in domains with significant computational and experimental costs, supporting informed decision-making and efficient resource utilization.",
"arxiv_id": "2601.05910",
"authors": [
"Yigitcan Comlek",
"R. Murali Krishnan",
"Sandipp Krishnan Ravi",
"Amin Moghaddas",
"Rafael Giorjao",
"Michael Eff",
"Anirban Samaddar",
"Nesar S. Ramachandra",
"Sandeep Madireddy",
"Liping Wang"
],
"categories": [
"stat.ML",
"cs.LG",
"stat.AP"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "Multi-task Modeling for Engineering Applications with Sparse Data",
"url": "https://arxiv.org/abs/2601.05910",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "c8dc1a41-48bb-4b9e-bf43-eb9d4db73a08",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}