Tutorials

ICDM 2024 will host three following tutorials:

  • Causality and Large Models
  • Hypergraph Neural Networks: An In-Depth and Step-by-Step Guide
  • Uncertain Boundaries: Multidisciplinary Approaches to Copyright Issues in Generative AI

You can find detailed information below.

Causality and Large Models

Presenters: Haoxuan Li, Chuan Zhou, Mengyue Yang, Mingming Gong, Jun Wang, Xiao-Hua Zhou

Abstract: Our tutorial aims to explore the synergies between causality and large models, also known as “foundation models,” which have demonstrated remarkable capabilities across for helping data mining in healthcare, finance, and education. However, there are increasingly concerns about the trustworthy and interpretability of these complex ”black-box” LLMs behind the promising performance in data mining domains. A growing community of researchers is turning towards a more principled framework to address these concerns, better understand the behavior of large models, and improve their reliability and interpretability. Specifically, this tutorial will focus on three directions: causal agents for decision-making, LLMs for causality, and benefiting LLMs with causality. Besides, we introduce some open challenges and potential future directions for this area. We hope this tutorial could stimulate more ideas on this topic and facilitate the development of causality-aware large models.

Duration: One whole Day (5 hrs)

Hypergraph Neural Networks: An In-Depth and Step-by-Step Guide

Presenters: Sunwoo Kim, Soo Yong Lee, Yue Gao, Alessia Antelmi, Mirko Polato, Kijung Shin

Abstract: Higher-order interactions (HOIs) are ubiquitous in real-world networks. Investigation of deep learning for networks of HOIs, expressed as hypergraphs, has become an important agenda for the data mining and machine learning communities. Thus, hypergraph neural networks (HNNs) have emerged as a powerful tool for representation learning on hypergraphs. Given the emerging trend, we provide a timely tutorial dedicated to HNNs. We cover the (1) inputs, (2) message passing schemes, (3) training strategies, (4) applications (e.g., recommender systems and time series analysis), and (5) open problems of HNNs. This tutorial is intended for researchers and practitioners who are interested in (hyper)graph representation learning and its applications.

Duration: Half-a-day (2.5 hrs)

Presenters: Archer Amon, Zichong Wang, Zhipeng Yin, Wenbin Zhang

Tutorial page: https://icdm2024-tutorial.github.io/index.html

Abstract: As generative AI systems become more prevalent in creative fields, concerns about intellectual property rights have grown, particularly regarding the production of content that closely resembles human-created work. Recent controversies, where AI models have generated near-replicas of copyrighted material, underscore the urgency of reviewing the current copyright framework and developing methods to mitigate infringement risks. To this end, this tutorial offers a comprehensive analysis of these copyright challenges, examining them throughout the AI development life cycle and providing developers with actionable strategies. It begins by discussing the foundational goals and considerations for copyright in generative AI, followed by methods for detecting and assessing potential violations in AI outputs. Next, it introduces techniques to safeguard creative works and datasets from unauthorized replication. The tutorial also covers training methods aimed at minimise the risk of AI models reproducing protected content. Finally, it reviews the state of AI copyright regulation and suggests future research pathways to address existing gaps.

Duration: Half-a-day (2.5 hrs)