BPOD 2025 : The Eighth IEEE International Workshop on Benchmarking, Performance Tuning and Optimization for Big Data Analytics and Big Models

The Eighth IEEE International Workshop on Benchmarking, Performance Tuning and Optimization for Big Data Analytics and Big Models (BPOD 2025)
Collocated at the 25th IEEE International Conference on Data Mining (ICDM 2025)

https://bdal.umbc.edu/bpod/bpod-2025/

Half day in November 12-15, 2025, Washington DC, USA

Description

Analysis of big data and applications of big models such as LLMs have become ubiquitous. Large machine learning models can have billions of parameters and are trained with terabyte (TB) to petabyte (PB) data. Compared to “small data” and “small models”, big data and big models often not only pose scalability challenges, but also pose challenges in optimizing and fine tuning algorithms or models. However, users of big data analytics or big models are most often not computer scientists. On the other hand, it is nontrivial for even experts to optimize and finetune big data analytic algorithms or big models because there are so many decisions to make. It is also challenging to compare the performance of different algorithms, systems, or models on a variety of tasks. To make things more complex, users may worry about not only accuracy or computational running time, response time or throughput, but also monetary cost, trustworthiness, security, privacy, and sustainability.

The aim of this workshop is to bring researchers and practitioners together to better understand the problems of optimization and performance tuning in big data analytics as well as big machine learning models, to propose new approaches to address such problems, and to develop related benchmarks, tools and best practices.
This workshop is built on top of the successful organization of previous workshops at the same conference.

Topics of interests include, but are not limited to:
- Optimization for machine learning and data mining algorithms for big data
- Optimization and fine tuning of big models, including model fine-tuning, prompt engineering, retrieval-augmented generation (RAG), etc.
- Performance tuning and optimization for analyzing specific data sets (e.g., scientific data, spatial data, temporal data, text data, images, videos, mixed datasets)
- Case studies and best practices for performance tuning and optimization for big data analytics or large models
- Trustworthiness, uncertainty, security, privacy, and other ethical considerations for big data analytics and large-language models (LLMs)
- Benchmark and comparative studies for big data analytics algorithms and big models
- Performance tuning and optimization for specific big data analytics algorithms, platforms, applications, or specific big models
- Optimization of big data analytic or big models on High Performance Computing (HPC) and Cloud environments
- Monitoring, analysis, and visualization of performance for big data analytics application and big models
- Workflow/process management & optimization in big data analytics environment
- Theoretical and empirical performance models for big data analytic applications and big models
- Self adaptive or automatic tuning tools for big data analytic applications or big models

Important Dates
- Paper Submission: Aug 29, 2025
- Decision Notification: Sep 15, 2025
- Camera-Ready Due Date: Sep 25, 2025
- Workshop Date: Tentatively on Nov 12, 2025 (the first day), but may be subject to change

Paper Submission (submission link will be provided soon)

Authors are invited to submit original papers, which have not been published elsewhere and which are not currently under consideration for another journal, conference or workshop. Paper submissions should be limited to a maximum of ten (10) pages, in the IEEE 2-column format (link), including the bibliography and any possible appendices. Submissions longer than 10 pages will be rejected without review. All submissions will be triple-blind reviewed by the Program Committee based on technical quality, relevance to scope of the conference, originality, significance, and clarity. The following sections give further information for authors. Please refer to the ICDM regular submission requirement for more information.

Submission site: https://wi-lab.com/cyberchair/2025/icdm25/scripts/submit.php?subarea=S17


Triple blind review: The authors shall omit their names from the submission. For formatting templates with author and institution information, simply replace all these information items in the template by “Anonymous”. In the submission, the authors should refer to their own prior work like the prior work of any other author, and include all relevant citations. This can be done either by referring to their prior work in the third person or referencing papers generically. For example, if your name is Smith and you have worked on clustering, instead of saying “We extend our earlier work on distance-based clustering (Smith 2019),” you might say “We extend Smith’s earlier work (Smith 2019) on distance-based clustering.” The authors shall exclude citations to their own work which is not fundamental to understanding the paper, including prior versions (e.g., technical reports, unpublished internal documents) of the submitted paper. Hence, do not write: “In our previous work [3]” as it reveals that citation 3 is written by the current authors. The authors shall remove mention of funding sources, personal acknowledgments, and other such auxiliary information that could be related to their identities. These can be reinstituted in the camera-ready copy once the paper is accepted for publication. The authors shall make statements on well-known or unique systems that identify an author, as vague in respect to identifying the authors as possible. The submitted files should be named with care to ensure that author anonymity is not compromised by the file names. For example, do not name your submission “Smith.pdf”, instead give it a name that is descriptive of the title of your paper, such as “ANewApproachtoClustering.pdf” (or a shorter version of the same).

Reproducibility requirement: Algorithms and resources used in a paper should be described as completely as possible to allow reproducibility. This includes experimental methodology, empirical evaluations, and results. Authors are strongly encouraged to make their code and data publicly available whenever possible. In addition, authors are strongly encouraged to also report, whenever possible, results for their methods on publicly available datasets.

Workshop proceeding: Accepted papers will be included in the ICDM Workshop Proceedings (separate from ICDM Main Conference Proceedings), and each workshop paper requires a full registration. Meanwhile, duplicate submissions of the same paper to more than one ICDM workshop are forbidden.

Workshop Chairs
- Zhiyuan Chen, University of Maryland, Baltimore County, U.S.A, zhchen-AT-umbc.edu
- Jianwu Wang, University of Maryland, Baltimore County, U.S.A, jianwu-AT-umbc.edu
- Feng Chen, University of Texas at Dallas, U.S.A, feng.chen-AT-utdallas.edu
- Junqi Yin, Oak Ridge National Laboratory, U.S.A, yinj-AT-ornl.gov

Program Committee (Tentative)
- Sahara Ali, University of North Texas, United States
- Antonio Badia, University of Louisville, United States
- Laurent D’Orazio, Rennes University, France
- Tome Eftimov, Jožef Stefan Institute, Slovenia
- Yanjie Fu, Arizona State University, United States
- Madhusudhan Govindaraju, Binghamton University, United States
- Marek Grzegorowski, University of Warsaw, Poland
- Xin Huang, Towson University, United States
- Shad Kirmani, LinkedIn Corp., United States
- Soufiana Mekouar, Mohammed V University Rabat, Morocco
- Baoning Niu, Taiyuan University of Technology, China
- Mijanur Palash, Oak Ridge National Laboratory, United States
- Frank Pallas, Paris Lodron University of Salzburg, Austria
- Lauritz Thamsen, University of Glasgow, United Kingdom
- Xiangfeng Wang, East China Normal University, China