This workshop tackles the challenge of transforming massive data into efficient representations through cutting-edge research in data representation and learning. We explore techniques that preserve semantic richness while optimizing computational efficiency, enabling faster processing with minimal resources. By reimagining the data-to-knowledge pipeline, we aim to build scalable, practical big data and AI systems. Join us to pioneer the next generation of intelligent systems that balance performance with sustainability.

This workshop provides a unique forum for in-depth discussion. We welcome submissions that are aligned with the workshop's thematic.

There are two ways to submit a paper: one option is to submit only the paper’s title and abstract; the other is to submit a regular or short paper, with regular papers limited to 8 pages and short papers to 4 pages (original manuscripts must be formatted as PDF files following the IEEE two-column conference format). Papers accepted under the second submission option will be published in the conference proceedings of IEEE Xplore. This workshop adopts a single-blind review policy.

You may submit your paper by emailing the organizer at: [email protected]

14:00 – 18:00, February 2 (Monday), 2026

Chair: Zhe Xue (Beijing University of Posts and Telecommunications)

• TTParser: Leveraging LLM for Enhanced Mapping of ATT&CK Tactics, Techniques, and Procedures in Unstructured Cyber Threat Intelligence

Yongxin Cai (Guangzhou University), Huacong Zhou (Guangzhou University), Zeyan Wang (Guangzhou University), Jingchao Chen (Guangzhou University), Zhenqi Cai (Guangzhou University), Jing Qiu (Guangzhou University), Zhe Li (Hebei Utilization and Planning Institute of Natural Resources)

• Pairwise Judgment Formulation for Semantic Embedding Model in Web Search

Mengze Hong (Hong Kong Polytechnic University), Di Jiang (Hong Kong Polytechnic University), Zichang Guo (Hong Kong Polytechnic University), Chen Jason Zhang (Hong Kong Polytechnic University)

• Trust-free Personalized Decentralized Learning

Yawen Li (Beijing University of Posts and Telecommunications), Yan Li (Beijing University of Posts and Telecommunications), Junping Du (Beijing University of Posts and Telecommunications), Yingxia Shao (Beijing University of Posts and Telecommunications), Meiyu Liang (Beijing University of Posts and Telecommunications), Guanhua Ye (Beijing University of Posts and Telecommunications)

• Enhancing GNN Learning on Relational Databases using Semantic Clustering-based Graph Enrichment

Hwiseung Son (Sungkyunkwan University), Kunyoung Kim (Sungkyunkwan University), Donggyu Kim (Sungkyunkwan University), Mye Sohn (Sungkyunkwan University)

• MiENet:A Mixture Expert Network for Dynamic Computing Resource Prediction

Mingdong He (Guangdong Power Grid Corporation), Zhaoyi Yang (Guangdong Power Grid Corporation), Chuangye Zhao (Guangdong Power Grid Corporation), Lei Xu (Guangdong Power Grid Corporation), Hao Wei (Guangdong Power Grid Corporation), Bo Li (Guangdong Power Grid Corporation), Xiaobo Huang (Guangdong Power Grid Corporation), Liquan Luo (Guangdong Power Grid Corporation)

Hongzhi Yin (The University of Queensland, Australia)

Yuankai Qi (Macqurie University, Australia)

Yongxin Tong (Beihang University, China)

Zhonghong Ou (Beijing University of Posts and Telecommunications, China)

Zhongying Zhao (Shandong University of Science and Technology, China)

Wanqi Yang (Nanjing Normal University, China)

Hao Wang (University of Science and Technology of China, China)

Wenbin Li (Nanjing University, China)

Lingling Zi (Chongqing Normal University, China)

Suguo Zhu (Hangzhou Dianzi University, China)