PFM4Cluster

The first Workshop on
Clustering in the Age of Pre-trained Foundation Models


In conjunction with ICDM 2026
The 26th IEEE International Conference on Data Mining

November 12-15, 2026, Shenyang, China

Topics of Interest

Call for papers


Clustering is a fundamental task in data mining that aims to partition unlabeled data into groups, such that data points within the same cluster exhibit semantic similarity. Recent advances in large-scale pre-trained foundation models (PFMs), including CLIP, LLMs, and MLLMs, have opened new directions for clustering research across images, texts, and graphs. This workshop offers a timely opportunity to bring together researchers and practitioners from multimodal learning, foundation models, and clustering. It will provide a platform for discussing recent advances, emerging methodologies, and practical applications. By fostering collaboration across these domains, the workshop aims to create new opportunities for addressing complex challenges at the intersection of foundation models and clustering.

Topics of Interest

This workshop welcomes all papers that are related but not limited to the following topics:
  • Theoretical foundations of PFMs for clustering
  • Parameter-efficient fine-tuning of PFMs for clustering
  • Model selection among a zoo of PFMs for clustering
  • Interpretability, Fairness, Robustness, and Privacy in PFMs-based clustering
  • PFMs-based clustering under fine-grained/continual/long-tailed environments
  • New datasets and benchmarks for PFMs-based clustering
  • Applications of PFM-based clustering in scientific domains, including programming languages, climate science, healthcare, life sciences, physics, and cognitive science
  • Surveys summarizing recent advances in using PFMs for clustering

Program

Thursday, November 12, 2026 · 3:50 PM-6:50 PM China Standard Time (UTC+8) · Grand Ballroom 3

TimeEventPresenter(s)
15:50-15:55Opening RemarkBo Peng (Host)
15:55-16:20Keynote Speech I: To Be Announced
16:20-16:45Keynote Speech II: To Be Announced
16:45-17:05Paper Session I: From Abstracts to Knowledge Graphs: Evaluating Relation Clustering and Post-hoc Canonicalization for General Health Information ExtractionAfra Alharbi, Hanan Murayshid, Rawad Alqahtani, Monira AlShehri, and Turky AlOtaiby
17:05-17:25Paper Session II: ARASH: Adaptive Retrieval And Shot Selection for Tabular PredictionSamirasadat Jamalidinan, Yue Xu, and Kazem Cheshmi
17:25-17:45Paper Session III: Skill-Delta Graphs for Career Transition Modeling: A Structural Analysis of Occupational Mobility from Unsupervised Role ArchetypesShreyash Rawat
17:45-18:05Paper Session IV: GeoSciLLM: Pretrained-Model-Based Clustering of Scientific Abstracts for Geo-Thematic Literature MappingVadim Tynchenko, Alexey Borodulin, Dmitry Martysyuk, Vladimir Nelyub, and Ivan Malashin
18:05-18:45Discussion and Q&ABo Peng (Host)
18:45-18:50Closing RemarkBo Peng (Host)

Accepted Papers

Four papers have been accepted for presentation at the workshop.

  1. From Abstracts to Knowledge Graphs: Evaluating Relation Clustering and Post-hoc Canonicalization for General Health Information Extraction Afra Alharbi, Hanan Murayshid, Rawad Alqahtani, Monira AlShehri, and Turky AlOtaiby
  2. ARASH: Adaptive Retrieval And Shot Selection for Tabular Prediction Samirasadat Jamalidinan, Yue Xu, and Kazem Cheshmi
  3. Skill-Delta Graphs for Career Transition Modeling: A Structural Analysis of Occupational Mobility from Unsupervised Role Archetypes Shreyash Rawat
  4. GeoSciLLM: Pretrained-Model-Based Clustering of Scientific Abstracts for Geo-Thematic Literature Mapping Vadim Tynchenko, Alexey Borodulin, Dmitry Martysyuk, Vladimir Nelyub, and Ivan Malashin

Keynote Speakers

Invited talks on clustering, foundation models, and intelligent reasoning.

Photo to be confirmed

Speaker to be confirmed

Affiliation to be confirmed

Title: To be confirmed

Abstract: To be confirmed

Bio: To be confirmed

Photo to be confirmed

Speaker to be confirmed

Affiliation to be confirmed

Title: To be confirmed

Abstract: To be confirmed

Bio: To be confirmed


Important dates

Submission deadlines are at 11:59 PM AOE (Anywhere on Earth).

Submission deadline: August 20, 2026
Paper notification: September 18, 2026
Camera-ready deadline: October 5, 2026
Workshop Date Thursday, November 12, 2026
Workshop Time 3:50 PM-6:50 PM China Standard Time (UTC+8)
Venue Grand Ballroom 3

Submission Guidelines

Paper Length and Submission Requirements

Authors are encouraged to submit original, English-language research contributions that have not been concurrently submitted or published elsewhere. All submissions must adhere to the IEEE 2-column format. For the regular paper track, submissions should not exceed 8 pages of content, plus an additional 2 pages for references. For the short paper track, submissions should be limited to a maximum of 4 pages of content, plus 1 extra page for references. Other submission requirements are same as ICDM 2026.

Review Guidelines

In alignment with the ICDM 2026 reviewing scheme, all submissions will undergo triple-blind reviews by Committee Members, evaluating technical quality, relevance to the conference scope, originality, significance, and clarity. All accepted papers will be presented as oral/poster presentations. By the unique ICDM tradition, all accepted workshop papers will be published in the dedicated ICDMW proceedings published by the IEEE Computer Society Press.

Registration and Attendance

At least one author per paper must register at the AUTHOR rate per paper. Student registration does not satisfy this requirement, even if the author is a student. At least one author of each accepted paper must present the paper at the conference for it to be included in the proceedings and program. In cases where an author is unable to attend the conference in person due to visa issues, a pre-recorded video presentation is allowed. The presenting author must still register for the conference.


Organizers

The organizing team is alphabetically ordered by surname

Program Co-chairs

Chunchun Chen Chunchun Chen Tongji University
Bo Peng Bo Peng University of Technology Sydney
Junming Shao Junming Shao University of Electronic Science and Technology of China
Xin Sun Xin Sun City University of Macau
Hanchen Wang Hanchen Wang University of Technology Sydney
Wei Ye Wei Ye Tongji University

Advisory Chair

Christian Böhm Christian Böhm University of Vienna

Publication Co-chairs

Wengang Guo Wengang Guo Tongji University
Xing Wei Xing Wei Tongji University
Jiayi Yang Jiayi Yang Tongji University

Program Committee Members

  • Zhengxuan Chen - Tongji University
  • Tongbo Guo - Tongji University
  • Bohan Li - Tongji University
  • Maozheng Li - Tongji University
  • Yang Liu - Shanghai Innovation Institute
  • Yue Niu - Tongji University
  • Zhaokai Sun - Tongji University
  • Chenrun Wang - Tongji University
  • Jinyang Wu - Shanghai Innovation Institute
  • Chenyi Xiong - Tongji University
  • Ziyang Zhu - Tongji University

Contact for information

If you have any questions regarding the workshop, feel free to reach out to us:
E-mail: Bo.Peng-7@student.uts.edu.au (Bo Peng), c2chen@tongji.edu.cn (Chunchun Chen)