PGM 2026 – The 13th International Conference on Probabilistic Graphical Models
- Valencia, Spain
- 9-11 September 2026
- Pre-conference workshop: 8 September 2026
The International Conference on Probabilistic Graphical Models (PGM) is a biennial international meeting that brings together researchers interested in all aspects of graphical models for probabilistic reasoning, decision making, and learning.
PGM 2026 is the 13th edition of the conference and will be held in Valencia, Spain, continuing a long-standing tradition of high-quality scientific contributions within an international research community spanning artificial intelligence, machine learning, and statistics.
PGM has traditionally been organized as a single-track, non-parallel conference, fostering broad engagement across topics and encouraging interaction among participants. Both theoretical and applied contributions are welcome.
Scope and Topics
We invite submissions of original, unpublished research papers on probabilistic graphical models and closely related areas, including (but not limited to):
- Probabilistic graphical models, including Bayesian networks, chain graphs, influence diagrams, sum–product networks, probabilistic relational models, and related frameworks
- Information processing in PGMs: such as exact and approximate inference, Monte Carlo methods, and variational approaches
- Structure learning, parameter learning, and causal discovery
- Causal modeling and causal inference
- Interpretable, explainable, and trustworthy AI based on graphical models
- Decision theory, reasoning under uncertainty, and sequential decision processes within graphical-model-based frameworks
- Connections between graphical models and deep learning, optimization, and statistical learning
- Scalable algorithms, software systems, and implementations for graphical models
- Applications of probabilistic graphical models in science, engineering, healthcare, economics, climate and environmental sciences, and other domains
Both methodological advances and application-driven contributions are welcome
Submissions and Review Process
Submissions should report on original research that has not been previously published and is not under review elsewhere. All submissions will undergo a rigorous peer-review process. Accepted papers will be presented at the conference and published in the Proceedings of Machine Learning Research (PMLR).
Papers must be submitted electronically via OpenReview: https://openreview.net/group?id=PGM/2026
Important Dates
- Submission site opens:
- Abstract submission deadline:
- Paper submission deadline:
- Author notification:
- Camera-ready deadline:
- Pre-conference workshop:
-
Conference dates:
September 09 - 11, 2026
Formatting and Templates
Submissions must follow the PGM formatting guidelines and be prepared exclusively in LaTeX. Authors are required to use the official template provided in the PGM 2026 Author Kit, available at
https://www.uv.es/pgm2026/assets/pgm2026_author_kit.zip.
The kit includes a sample paper with detailed formatting instructions.
Submissions are limited to 12 pages, excluding references. Depending on the number of accepted papers, contributions may be presented either as oral presentations or poster presentations at the conference. However, no distinction is made between presentation formats in the conference proceedings.
Generative AI Considerations
Authors are allowed to use generative AI tools such as Large Language Models (LLMs) to assist in writing or research. However, authors must take full responsibility for all content in their paper, including any content generated by AI tools that might be construed as plagiarism or scientific misconduct. We encourage authors to explain any notable ways in which these tools were used in their research methodology. LLMs are not eligible for authorship.
Pre-conference Workshop
PGM 2026 will be preceded by a one-day workshop on Causal Probabilistic Graphical Models for Earth System Science on 8 September 2026. Further details will be announced in due course.
IJAR Special Issue
Selected papers presented at PGM 2026 will be invited to submit extended versions to a special issue of the International Journal of Approximate Reasoning (IJAR).
Registration
At least one author of each accepted paper is required to register for the conference.
Registration information will be provided in due course on the conference website (https://www.uv.es/pgm2026/).
Program Chairs
- Gherardo Varando (Universitat de València)
- Manuele Leonelli (IE University, Madrid)
- Gustau Camps-Valls (Universitat de València)