Robust Machine Learning in Open Environments
Workshop at the Conference on Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) 2024
This workshop aims to keep track of recent advances and discuss future research about robust machine learning in open environments. By bringing together practice, methodology, and theory actors we aim at identifying unexplored areas and pushing the frontier of robust machine learning problems.
The workshop will be held on Taipei International Convention Center, May 7, 2024 - we look forward to seeing you!
Call for Papers
We invite researchers from related fields to submit their recent work to our workshop. All accepted papers will be presented in the workshop.
Topics
We encourage submissions related (but not limited) to the following topics:
- Algorithms and theories for robustness in various open environment problems, e.g., emerging new class, decremental/incremental features, changing data distributions, long-tailed distributions, varied learning objectives;
- Algorithms and theories for robustness of various learning paradigms, e.g., self-supervised learning, semi-supervised learning, reinforcement learning, federated learning, few-shot learning, prompt learning, transfer learning;
- Algorithms and theories for robustness of various models, e.g., transformer, graphical model, large-language models, vision-language models;
- Robust machine learning for science and social good, such as robust machine learning for healthcare, climate change, fairness, etc.
Important Dates
- Paper Submission Deadline: February 7, 2024
- Paper Acceptance Notification: February 29, 2024
- Camera Ready Papers Due: March 13, 2024
*All deadlines are 23:59 Pacific Standard Time (PST)
Submission Details
To ensure your submission is considered, please adhere to the following guidelines:
- Formatting Instructions: Use the template when preparing your submission. Papers need to be prepared and submitted as a single PDF file and should not exceed 8 single-spaced pages. While your submission can contain a supplement or appendix, please note that reviewers are not obliged to review supplementary material.
- Reviews: The review process will be double-blind. All submissions must be anonymized and the leakage of any identification information is prohibited.
To submit your work, please visit the Submission Site.
Schedule
Time | Event |
---|---|
13:40 -- 13:45 | Opening Ceremony |
13:45 -- 14:30 | Keynote: Effective Pre-Trained Models Selection with Meta Representation.
Han-Jia Ye, Associate Professor, Nanjing University. |
14:30 -- 15:15 | Keynote: A Model Collaboration Perspective for LLM-Driven Data Annotation.
Haobo Wang, Assistant Professor, Zhejiang University. |
15:15 -- 15:30 | Coffee Break |
15:30 -- 15:45 | Abductive Learning for Neuro-Symbolic Grounded Imitation. Jie-Jing Shao, Hao-Ran Hao, Xiao-Wen Yang, De-Chuan Zhan. |
15:45 -- 16:00 | A Bias in Training Data Degrades the Quality of Variable Importance Scores of Random Forests. Shuhei Kimura, Yuasa, Kenta, Tokuhisa Masato. |
16:00 -- 16:15 | An Unbiased Risk Estimator for Partial Label Learning with Augmented Classes. Jiayu Hu, Beibei Li, Senlin Shu. |
16:15 -- 16:30 | DeepInception: Hypnotize Large Language Model to Be Jailbreaker. Xuan Li, Zhanke Zhou, Jianing Zhu, Jiangchao Yao, Tongliang Liu, Bo Han. |
16:30 -- 16:45 | Prompt Tuning for Natural Language to SQL with Embedding Fine-Tuning and Retrieval Augmented Generation. Jisoo Jang, Tien-Cuong Bui, Yunjun Choi, Wen-Syan Li |
16:45 -- 17:00 | Variations in Retrieval Quality: Query, Answer, and Relation Features. YoungJoon Park, Wen-Syan Li. |
Organizers
Lan-Zhe Guo, Nanjing University, China.
Tong Wei, Southeast University, China.
Yu-Feng Li, Nanjing University, China.
Min-Ling Zhang, Southeast University, China.