The 2nd Workshop on Advances in Robust and Reliable Machine Learning (ARRML’25)

Held in conjunction with SIAM International Conference on Data Mining (SDM) 2025

May 3, 2025, Alexandria, Virginia, USA

Introduction

In recent years, machine learning models have achieved remarkable success across diverse applications, yet concerns regarding their reliability, robustness, and trustworthiness persist, especially when deployed in real-world environments. The dynamic nature of data, distribution shifts, and the potential for unpredictable scenarios make it imperative to develop models that can perform reliably under varying conditions.

This workshop aims to bring together researchers and industry practitioners to explore cutting-edge techniques, emerging opportunities, and future directions in building more trustworthy and resilient machine learning systems. Topics of interest include trustworthy machine learning, out-of-distribution generalization under domain shifts, comprehensive model robustness analysis, data sufficiency and representativeness, and strategies for runtime monitoring and assurance.

By featuring keynote talks, paper presentations, and interactive discussions, this workshop will serve as a premier platform for exchanging innovative ideas and fostering collaborations across diverse backgrounds. Participants will gain insights into state-of-the-art advancements, challenges, and best practices in creating machine learning models that can meet the demands of real-world applications with enhanced reliability and robustness.

Call for Papers

Important Dates:

Following are the proposed important dates for the workshop. All deadlines are due 11:59 pm Anywhere on Earth (AOE).

Paper submission: March 24, 2025
Notification of decision: March 31, 2025
Camera-ready due: April 5, 2025
Workshop date: May 3, 2025, 8:00 AM - 3:30 PM, Room: Bell, [Link]

Topics of Interest:

We encourage submissions in various degrees of progress, such as new results, visions, techniques, innovative application papers, and progress reports under the topics that include, but are not limited to, the following broad categories:

Domain adaptation and generalization
Distributional robust optimization
Causal inference
Transfer learning
Data augmentation and generalization
Disentangled representation learning
Invariant learning
Out-of-distribution detection, novelty detection, anomaly detection
Open set recognition
Uncertainty quantification
Sensory and semantic anomaly detection
Model robustness analysis
Data sufficiency and representativeness analysis
Runtime monitoring and assurance

Submission Guidelines:

Submissions are limited to a total of 5 pages, including all content and references. There will be no page limit for supplemental materials. All submissions must be in PDF format and formatted to IEEE Computer Society Proceedings Manuscript Formatting Guidelines (two-column format).

Template guidelines are here: https://www.ieee.org/conferences/publishing/templates.html.

Following the SDM conference submission policy, reviews are double-blind. Submitted papers will be assessed based on their novelty, technical quality, potential impact, and clarity of writing. For papers that rely heavily on empirical evaluations, the experimental methods and results should be clear, well-executed, and repeatable. Authors are strongly encouraged to make data and code publicly available whenever possible. The accepted papers will be posted on the workshop website but will not be included in the main conference proceedings.

Submit your papers through the website: https://cmt3.research.microsoft.com/ARRML2025/Submission/Index.

Upon notification, we ask that authors of accepted works make any final changes and then submit a camera-ready version to the submission site. The workshop website will then be updated with links to accepted papers. Note that accepted works will not be formally published. This means that:

- Authors can retain full copyright of their works.
- Works in accepted papers by this workshop are not precluded from being published in other research venues.
- Submitted papers are allowed to have significant overlap with previously published or currently submitted work (in this case, previously published papers are welcomed).

Any questions regarding submissions can be directed to chen_zhao@baylor.edu.

Accepted Papers

Oral Papers

Meta-Learning Based Few-Shot Graph-Level Anomaly Detection
- Li Liting, Yumeng Wang, Sun Yueheng
Network Anomaly Detection Algorithm based on Hyperbolic Space
- Zhitao Ma, Wenjun Wang, Yueheng Sun
NeuroScan AI: Early Alzheimer’s Detection
- Gyan Chand Yadav, Anuj Kumar, Aryan Mehta, Abhijeet Gupta, Aman Sharma
Perceptive Multimodal Generative AI
- Sidesh Sundar S, Rithani M, Vimal Dharan N, SyamDev R S
Underwater Debris Detection Using Machine Learning
- Shailaja Uke, Nomaan Shaikh, Shruti Saswade, Srushti Satte, Sanket Palkar, Nomaan Shaikh
Detection of Cancer Cells
- Abhi Grover, Aditya Kumar Gupta, Kamal Kumar, Rishabh Bhardwaj, Shobhit Sharma, Pratik Pramanik
QuCumber: Wavefunction Reconstruction with Neural Networks
- Aditya Patel
Understanding the Uncertainty of LLM Explanations from Reasoning Topology
- Longchao Da, Xiaoou Liu, Jiaxin Dai, Lu Cheng, Yaqing Wang, Hua Wei
Towards Generalizable Multi-Modal Forgery Detection: A Survey of Recent Advances and Open Challenges
- Xinyu Wu, Chen Zhao
Fake Image Detection: A Novel Approach for Robust Identification
- Xiaohui Chen, Chen Zhao
Enhancing Preliminary Diagnosis Through Intelligent Decision Support
- Ashutosh Ahuja, Mandakini Gupta

Abstract Papers

A Machine Learning Approach to Early-Stage Failure Prediction in Traction Motor Manufacturing
- Pooja Gaikwad, Kapilraj Nangare, Chaitanya Suryawanshi
Enhancing Cyber Defense through Machine Learning
- Ayush Thakur, Disha Sharma, Aakash Ojha

Workshop Schedule

May 3, 2025, 8:00 AM - 3:30 PM, The Westin Alexandria Old Town Hotel, Room: Bell, [Link]

For virtual presentations, please use the Zoom link: [Link]

8:00 am - 8:10 am

Opening Remarks

8:10 am - 9:10 am

Keynote Talk 1: Dongjie Wang, University of Kansas

9:10 am - 10:10 am

- Keynote Talk 2: Kunpeng Liu, Portland State University

10:10 am - 11:10 am

- Keynote Talk 3: Yi He, The College of William & Mary

11:10 am - 12:10 pm

- Accepted Paper Talks 1
  - Meta-Learning Based Few-Shot Graph-Level Anomaly Detection
    - Li Liting, Yumeng Wang, Sun Yueheng
  - Network Anomaly Detection Algorithm based on Hyperbolic Space
    - Zhitao Ma, Wenjun Wang, Yueheng Sun
  - NeuroScan AI: Early Alzheimer’s Detection
    - Gyan Chand Yadav, Anuj Kumar, Aryan Mehta, Abhijeet Gupta, Aman Sharma
  - Perceptive Multimodal Generative AI
    - Sidesh Sundar S, Rithani M, Vimal Dharan N, SyamDev R S

12:10 pm - 1:30 pm

- Lunch Break

1:30 pm - 2:30 pm

- Accepted Paper Talks 2
  - Underwater Debris Detection Using Machine Learning
    - Shailaja Uke, Nomaan Shaikh, Shruti Saswade, Srushti Satte, Sanket Palkar, Nomaan Shaikh
  - Detection of Cancer Cells
    - Abhi Grover, Aditya Kumar Gupta, Kamal Kumar, Rishabh Bhardwaj, Shobhit Sharma, Pratik Pramanik
  - QuCumber: Wavefunction Reconstruction with Neural Networks
    - Aditya Patel
  - Understanding the Uncertainty of LLM Explanations from Reasoning Topology
    - Longchao Da, Xiaoou Liu, Jiaxin Dai, Lu Cheng, Yaqing Wang, Hua Wei
  - Enhancing Preliminary Diagnosis Through Intelligent Decision Support
    - Ashutosh Ahuja, Mandakini Gupta

2:30 pm - 3:30 pm

- Keynote Talk 4: Xujiang Zhao, NEC Laboratories America

3:30 pm - 3:35 pm

Closing

Invited Speakers

Dongjie Wang, University of Kansas

Short bio: Dr. Dongjie Wang is an assistant professor in the Department of Electrical Engineering and Computer Science at the University of Kansas. His research focuses on data-centric AI, causal graph learning, spatial-temporal data mining, user profiling, and graph mining. During his Ph.D., he interned at prestigious institutions like Nokia Bell Labs, NEC Labs America, and JD.COM Silicon Valley Research Center. He has published over 30 papers in leading journals (e.g., TKDE, KAIS) and conferences (e.g., NeurIPS, KDD, AAAI, WWW). Three of his papers (SIGSPATIAL, ICDM1, ICDM2) were best paper runner-ups, and his NeurIPS paper was a spotlight. His work on automated urban planning received media coverage from Synced AI and UCF Today. He also serves as a PC member for conferences and journals such as KDD, IJCAI, AAAI, WSDM, CIKM, TNNLS, KBS, and TKDD.

Kunpeng Liu, Portland State University

Short bio: Dr. Kunpeng Liu is an assistant professor in the Department of Computer Science at Portland State University. He received his Ph.D. degree from the Department of Computer Science, University of Central Florida, Orlando, FL in 2022. He received both an M.E. degree and a B.E. degree from the Department of Automation, University of Science and Technology of China (USTC), Hefei. He has broad interests in data-centric AI (DCAI), large language models (LLMs), and reinforcement learning (RL), especially in efficient fine-tuning and effective reasoning of LLMs, with application to big data problems, including traceable and explainable feature engineering, reasoning on recommender systems, and spatiotemporal user behavior analysis. He has published more than 60 papers in refereed journals and conference proceedings. He serves as AC/SPC/PC for various conferences, including ICML, ICLR, NeurIPS, KDD, ICDM, SDM, WWW, CIKM, IJCAI, and AAAI. He has co-organized one tutorial and five workshops on DCAI. He is the Financial Chair of IEEE ICKG 2024 and Registration Co-Chair of IEEE BigData 2024. He is a recipient of the Best Paper Runner-up Award from IEEE ICDM 2021. He is a recipient of the NSF CRII Award.

Yi He, The College of William & Mary

Short bio: Dr. Yi He is an assistant professor of Data Science with the School of Computing, Data Science, and Physics at William & Mary. Prior to that, he had been with the Department of Computer Science at Old Dominion University since 2021. He received his Ph.D. from the Center for Advanced Computer Studies (CACS) at the University of Louisiana at Lafayette in 2020, advised by Dr. Xindong Wu, and his B.E. from Harbin Institute of Technology (HIT), China, in 2013. His research interests include data mining, streaming algorithms, graph learning, and AI for conservation study. He is a recipient of the IEEE TCII Volunteer Award 2022 and the NSF CRII Award 2023.

Xujiang Zhao, NEC Laboratories America

Short bio: Dr. Xujiang Zhao is a research staff member at NEC Laboratories America. He received his Ph.D. in the Computer Science Department at The University of Texas at Dallas in 2022. Dr. Zhao has published his work in top-tier machine learning and data mining conferences, including NeurIPS, AAAI, ICDM, and EMNLP. He also served on technical program committees for several high-impact venues, such as ICML, NeurIPS, ICLR, KDD, and AAAI.

Organizers