Int-2502- Intern In Visualization Of Graph Learning For Literature Review And Paper Screening

Internship contract – 6 months | Fulltime/40h | From 01.03.2025 on | Belval

Are you passionate about research? So are we! Come and join us

The Luxembourg Institute of Science and Technology (LIST) is a Research and Technology Organization (RTO) active in the fields of materials, environment and IT. By transforming scientific knowledge into technologies, smart data and tools, LIST empowers citizens in their choices, public authorities in their decisions and businesses in their strategies.

https://www.list.lu/

How will you contribute?

Conducting a literature review is a tedious, time-consuming process where analysts manually screen thousands of research papers to assess their relevance. Their end goal is to select only the few papers of interest from a large corpus obtained by querying multiple databases, through paper screening: an iterative process of elimination and classification into "relevant" or "irrelevant" papers. While semi-supervised machine learning approaches can accelerate this process, they often lack the interpretability and transparency required by analysts and regulatory bodies, especially in sensitive areas such as healthcare. Moreover, these models face challenges due to the severe imbalance between the large number of "irrelevant" papers and the very few "relevant" ones, which can degrade their performance.

Graph learning offers a promising alternative, using relationships to propagate labels across a graph structure and making this process visual and interpretable. Previous work at LIST demonstrated that graph learning algorithms can achieve performance comparable to conventional machine learning methods in this context. However, to fully explore the potential of graph learning in paper screening, a complete workflow is required—from graph construction to label propagation and interactive visualization of the results. This internship aims to integrate a reusable pipeline that facilitates the entire process, enabling researchers to better understand the graph learning approach and assess its efficiency in various scenarios.

As an intern, you will be mainly in charge of:

• Developing a graph learning pipeline for paper screening, from graph construction through classification and label propagation to visualization, simulating a semi-supervised approach.
• Creating interactive visualizations (with JavaScript and libraries like D3.js) to illustrate label propagation across the graph, enhancing interpretability and transparency for users.
• If time allows, exploring ‘researcher-in-the-loop’ interfaces for paper screening, ensuring transparency in label propagation and allowing for researcher adjustments.
• Evaluating the impact of different data inputs, graph construction methods, and classifier variations on performance.
• Interpreting and comparing classification results through metrics (accuracy, computation time...)
• Communicating your progress in weekly meetings.
• Writing clean, reusable code.
• Documenting your work in a comprehensive report for future reference, covering the pipeline, visualizations, key findings, and recommendations.

Related readings:

• van de Schoot, R., de Bruin, J., Schram, R. et al. An open source machine learning framework for efficient and transparent systematic reviews. Nat Mach Intell 3, 125–133 (2021). https://doi.org/10.1038/s42256-020-00287-7
• C. Chen et al., "Interactive Graph Construction for Graph-Based Semi-Supervised Learning" in IEEE Transactions on Visualization & Computer Graphics, vol. 27, no. 09, pp. 3701-3716, Sept. 2021, doi: 10.1109/TVCG.2021.3084694.

Is Your profile described below? Are you our future colleague? Apply now!

Education

• Master’s student in Computer Science, Data Science, or a related field

Experience and skills

• Proficiency in Python and JavaScript; interest in learning to use additional libraries as needed
• Familiarity with Git version control
• Knowledge of or interest in graphs, graph learning, and data visualization techniques

Language skills

• Proficiency in English for a professional work environment; French is a plus

Your LIST benefits

• An organization with a passion for impact and strong RDI partnerships in Luxembourg and Europe that works on responsible and independent research projects;
• Sustainable by design, empowering our belief that we play an essential role in paving the way to a green society;
• Innovative infrastructures and exceptional labs occupying more than 5,000 square metres, including innovations such as our Viswall, high-scale incubators and top of the range 3D/4D printings that are part of our toolkit for excelling in all we do;
• Multicultural and international work environment with more than 45 nationalities represented in our workforce;
• Diverse and inclusive work environment empowering our people to fulfil their personal and professional ambitions;
• Gender-friendly environment with multiple actions to attract, develop and retain women in science;
• 32 days’ paid annual leave for a full time internship, 11 public holidays per annum, flexible working hours,
• An environment encouraging curiosity, innovation and entrepreneurship in all areas.
  

Apply online

https://www.list.lu/en/jobs/interns/

Your application must include a motivation letter oriented towards the position and detailing your experience

Application procedure and conditions:

We kindly request applicants to provide their nationality for statistical purposes only, as part of our commitment to promoting diversity and ensuring equal opportunities in our workforce. This information will be kept confidential and will not be used for any discriminatory purposes.

LIST is dedicated to maintaining an inclusive work environment and is an equal opportunity employer. We are committed to attracting, hiring, and retaining a diverse workforce. All applicants will be considered for employment without discrimination based on national origin, race, color, gender, sexual orientation, gender identity, marital status, religion, age, or disability.

Applications will be continuously reviewed until the position is filled. An assessment committee will thoroughly evaluate applications, adhering to guidelines designed to ensure equal opportunities. The primary criteria for selection will be the alignment of the applicant's existing skills and expertise with the requirements mentioned above.