Call for Papers

In manufacturing, the traditional process optimization, diagnostics, and maintenance of systems depended largely on domain engineer's knowledge and expertise. This practice is not sufficient anymore for the contemporary manufacturing requirements. Machine Learning and AI may enhance the automation in monitoring, diagnostics, and control for High Volume Manufacturing, and provide domain engineers with the necessary tools for more effective process optimization. However, several key challenges are faced when applying ML and AI techniques in this field: 

• Often only small amounts of labelled data are available in contrast to very complex high-dimensional problem spaces, and this data may be biased or imbalanced to specific scenarios or contexts. To this end, techniques exploiting human experts and integration of domain knowledge in the learning or reasoning is studied and applied.

• Also, most manufacturing use cases require interpretability and uncertainty quantification because AI predictions are expected to contribute to decisions on processes with high financial impact. Thus, advanced visualisation and methods to enhance interpretability are necessary.

• Finally, due to the physical complexity of the systems, problems like concept drift quickly arise, warping the problem space through time.

The aim of this workshop, held on Friday 22 September, 2023, is to be a discussion forum for the most recent advances on these topics in the broad area of manufacturing and specifically including the semiconductor manufacturing industry.

We encourage both theoretical and practical contributions to stimulate interactions between participants, by mixing longer mature contributions with short, open for discussion, ideas.

Submission information

We invite contributions of the following types:

• full research papers [10-16 pages] to present new substantial research,

• short (e.g., work-in-progress or position) papers [5-9 pages] to present ongoing and preliminary works,

• extended abstracts of already published work [2-6 pages],

• demos [2-6 pages].

Mode of presentation: All papers accepted to the workshop can be presented as a poster (or demo; if applicable) during a poster session, and a few (to the extent that time allows; depending on the number of contributions) also by means of an oral presentation.

Publication of papers: Full papers are published in a joint workshop proceedings arranged by ECML-PKDD, but authors may opt-out if they do not want their paper to be included. Short papers, abstracts of existing work, and demo papers will be featured on the workshop webpage, but not included in any formal proceedings.

For extended abstracts of work already published elsewhere, please include full citation for the original paper (note that published means it has appeared in an archived conference proceedings or journal). Please include the original paper as an appendix at the end of the PDF (only for review, we can link to the original paper but we will not post a copy of your original paper on the website).

For demo papers, we encourage you to include a link to a (short) video in the paper.

Formatting requirements. Authors should indicate in their abstracts the kind of submission, to help reviewers better understand their contributions. Submissions must be in PDF, written in English, not longer than 16 pages (including references), and formatted according to the standard Springer CCIS style. The CCIS webpage can be found here and the template is here. Author names may be included (single-blind review).

Other requirements. For accepted papers, at least one author must register for the conference and attend the workshop in person to present the work.

Submit via the ECML-PKDD workshop & tutorial track CMT. Make sure to select the “AI4M: AI for Manufacturing” workshop: https://cmt3.research.microsoft.com/ECMLPKDDworkshop2023/Track/32/Submission/Create

Topics of interest are all aspects of AI for Manufacturing, with a specific interest for methods and tools to address the key challenges for applications in manufacturing:

1. ML when labelling is expensive: active learning, semi-supervised learning, weak supervision, transfer learning. Techniques to maximally learn from small sample sizes, together with expert input. 

2. Advanced visualisations for human expert interactions and interpretability: Dimensionality reduction, representation learning, embeddings. 

3. Embedding domain expertise in ML: graphical models, physics-aware ML architectures, integration of simulation models (digital twins+ML), or other combinations of reasoning and learning frameworks. 

4. Uncertainty quantification and learning with noisy data, or learning with only positive and unlabeled examples. 

5. Assessment of the impact of noise, bias, outliers on model performance, ML for improving data quality, data-centric AI.

6. Techniques for detecting and addressing concept drift. 

Important Dates (all times are 23:59pm Anywhere-on-Earth timezone, UTC-12):

Submission: June 12 June 19, 2023 (extended)

Notification: July 12, 2023

Camera-ready: August 17, 2023

Workshop date: September 22, 2023

Further information and enquiries:

Organizers: Jefrey Lijffijt (Ghent University), Dimitra Gkorou (ASML), Pieter Van Hertum (ASML), Mykola Pechenizkiy (TU Eindhoven)

Website: https://sites.google.com/view/ai4manufacturing

Submission url: https://cmt3.research.microsoft.com/ECMLPKDDworkshop2023/Track/32/Submission/Create

Contact email: ai4manufacturing _at_ gmail.com