PhD forum

ICDM 2025 PhD Forum

Co-Chairs: Olga Andreeva, Lijing Wang, Vagelis Papalexakis
Date: November 14, 2025
Room: South American B

Schedule

  • 13:30 - 13:35: Opening
  • 13:35 - 14:40: Fireside chat with Prof. Aidong Zhang
  • 14:40 - 15:30: Keynote 1 - Dr. Puja Das (Apple)
  • 15:30 - 16:00: Coffee Break
  • 16:00 - 16:50: Keynote 2 - Dr. Hua Wei (ASU)
  • 16:50 - 17:30: Student Presentations (8 mins per paper)

Program Details

Fireside chat with Prof. Aidong Zhang

Prof. Aidong Zhang

During this fireside chat we are going to have a discussion with Dr. Zhang about graduate research, thriving during graduate school, employment prospects after graduation. We will also solicit and discuss questions from the audience.

Bio: Dr. Aidong Zhang is Thomas M. Linville Professor of Computer Science in the School of Engineering and Applied Sciences at University of Virginia (UVA). She also holds joint appointments with the Department of Biomedical Engineering and School of Data Science at University of Virginia. Her research interests include machine learning, data mining, bioinformatics, and health informatics. Dr. Zhang and her students won the ACM KDD 2025 best paper award in research track. Dr. Zhang is a fellow of ACM and IEEE and a fellow of the American Institute for Medical and Biological Engineering (AIMBE). Dr. Zhang is also a member of the Virginia Academy of Science, Engineering and Medicine.

Keynote Speakers:

Keynote Speaker: Dr. Puja Das (Apple)

Dr. Puja Das

Abstract: Transitioning from academia to industry is both exciting and challenging. In this talk, Dr. Das shares her journey from researching online convex optimization during her PhD to leading large-scale applied ML teams at Apple, Twitter (X), and Warner Bros. Discovery. She discusses how to translate deep technical expertise into real-world impact, stay relevant amid rapid advances in AI/ML, and navigate complex problem spaces within large organizations. Drawing from personal experiences, Dr. Das reflects on finding balance between curiosity-driven exploration and business value, managing uncertainty, and continually aligning research interests with product impact. Her talk offers early-career researchers practical insights on building an impactful, resilient, and purpose-driven career in applied machine learning.

Bio: Dr. Puja Das is a senior machine learning leader at Apple, where she heads multiple ML teams driving innovation across ads prediction, quality, and signal intelligence for Apple’s large-scale advertising platforms. Her work lies at the intersection of machine learning, optimization, and personalization, with applications that impact billions of users worldwide. Puja’s career spans over a decade of pioneering contributions across industry-leading organizations, including Twitter (now X) and Warner Bros. Discovery, where she led global teams advancing state-of-the-art personalization, search, and recommendation systems. Her leadership has shaped the deployment of large language models, multimodal models, and bandit-based optimization frameworks in real-world, high-scale environments such as the App Store, Apple Books and Max/HBOMax. An active researcher, Puja’s work has been published in top-tier venues including KDD, ACM RecSys, AAAI, CIKM, and IEEE BigData, and her inventions include patents on meta-learning frameworks and bandit optimization for recommendations. She holds a Ph.D. in Computer Science from the University of Minnesota, where her doctoral research focused on online convex optimization and portfolio selection, and is a recipient of the prestigious IBM PhD Fellowship Award. Beyond her technical leadership, Puja is deeply committed to mentorship and advancing diversity in AI. She has served as a keynote and featured speaker at global AI and ML conferences and continues to mentor early-career researchers navigating the transition from academia to applied machine learning.

Keynote Speaker: Dr. Hua Wei (Arizona State University)

Dr. Hua Wei

Talk Title: Real-world AI Agents: Stories on Stage and Behind the Scenes

Abstract: AI agents powered by reinforcement learning (RL) and large language models (LLMs) have demonstrated remarkable success in domains such as gaming and robotics, sparking growing interest in their potential for real-world decision-making. However, applying agents to real-world settings introduces significant challenges, including data sparsity, limited generalization, and complex real-world constraints. In this talk, I will discuss how these challenges shape the practicality of AI agents in urban domains and present our research efforts to address them. I will also share personal insights and experiences from behind the scenes of these research journeys.

Bio: Hua Wei is an Assistant Professor in the School of Computing and Augmented Intelligence (SCAI) at Arizona State University (ASU). He received his Ph.D. from Penn State in 2020. His research interests include data mining and machine learning, with a focus on spatio-temporal data mining and reinforcement learning. His work has appeared in leading venues such as NeurIPS, ICML, AAAI, CVPR, KDD, IJCAI, ECML-PKDD, and WWW, and has received multiple Best Paper Awards from ECML-PKDD and ICCPS. His research is supported by the National Science Foundation (NSF), Department of Energy (DoE), and Department of Transportation (DoT). Dr. Wei is also a recipient of the Amazon Research Award, Cisco Research Award, and the NSF CAREER Award (2025).


Accepted Student Papers

  • “LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection”, Xinyue Zeng
  • “Open-World Long-Tail Learning”, Haohui Wang
  • “HiSLR: Sample-Specific Relationships in Hyperbolic Space for Hierarchical Text Classification”, Ashish Kumar and Durga Toshniwal
  • “LLM-Based Construction of Knowledge Graphs for the Analysis of Human Smuggling Networks”, Dipak Meher and Carlotta Domeniconi
  • “MetamatBench: Integrating Heterogeneous Data, Computational Tools, and Visual Interface for Metamaterial Discovery”, Jianpeng Chen