Call for Chapters — Edited Volume “Multi-Task Learning in Engineering”
Published by: Springer-Nature
Book Series: Springer Optimization and Its Applications (SOIA)
Series URL: https://link.springer.com/series/7393
Dear Colleagues,
We are pleased to invite researchers, scholars, and leading practitioners to contribute original book chapters to the forthcoming edited volume entitled “Multi-Task Learning in Engineering”, to be published within the prestigious Springer Optimization and Its Applications (SOIA) series.
Following the successful publication of our first volume, “Multi-Task Learning in Science” (https://link.springer.com/book/9783032299963), this second volume shifts the paradigm toward the engineering domain.
The book aims to provide a comprehensive, state-of-the-art overview of recent theoretical breakthroughs, algorithmic innovations, and computational frameworks at the intersection of Deep Learning, Generative AI, and Multi-Task Learning (MTL).
Scope and Core Themes:
This volume specifically investigates how multi-task architectures can mitigate computational bottlenecks, exploit cross-domain synergies, and optimize inductive bias across complex engineering systems. We solicit high-quality contributions addressing—but not limited to—the following thematic areas:
* Methodological & Theoretical Advancements: Novel MTL architectures, Pareto optimization in many-task learning, loss-balancing strategies, and gradient conflict resolution.
* Generative AI & Foundational Models: The integration of MTL with large-scale generative models and self-supervised frameworks for engineering tasks.
* Biomedical & Healthcare Engineering: Multi-task predictive modeling, medical imaging, and biosignal processing.
* Robotics & Autonomous Systems: Multi-modal perception, sensor fusion, and intelligent control systems. * Industrial Automation & Smart Manufacturing: Predictive maintenance, digital twins, and cyber-physical systems optimization.
* Materials Science & Computational Design: Multi-property material discovery and molecular property prediction.
Submission Typologies:
To ensure a well-rounded and impactful reference volume, we welcome the following types of submissions:
1. Original Research Chapters: Presenting novel methodologies, rigorous theoretical frameworks, or pioneering empirical results.
2. Comprehensive Surveys & Critical Reviews: Offering systematic insights into current trends, open challenges, and future trajectories of MTL in engineering.
3. Advanced Industrial Case Studies: Documenting large-scale, real-world deployment, scalability analysis, and operational performance of MTL paradigms.
Manuscript Specifications: Each chapter should be comprehensive, spanning between 20 and 40 pages, inclusive of all figures, tables, and bibliographic references.
There are no fees for publishing the chapter in the Edited Book.
Deadlines:
Submission of Expression of Interest (EoI) (Tentative Title & Abstract): August 1, 2026
Full Chapter Manuscript Submission: October 1, 2026
Notification of Peer-Review Results & Editorial Feedback: December 1, 2026
Camera-Ready / Final Revised Chapter Submission: February 1, 2027
Submission Guidelines:
Manuscripts must be submitted electronically via email to the centralized editorial address: multitasklearning.book@gmail.com
Authors are kindly requested to include the Editorial Board in copy (CC):
* pardalos@ufl.edu
* giuseppe.nicosia@unict.it
* giulio.giaquinta7@gmail.com
Editorial Board:
* Prof. Panos Pardalos — University of Florida, USA
* Prof. Giuseppe Nicosia — University of Catania, Italy
* Dr. Giulio Giaquinta — University of Padova, Italy
Should you require any further information regarding the alignment of your research topic with the scope of this volume, please do not hesitate to contact the editors.
We look forward to your distinguished contributions to this landmark volume.
Sincerely,
The Editorial Board.
