Materials

Slides for the tutorial: https://github.com/QueuQ/CGL_AAAI2024/blob/master/tutorial_slides.pdf

Our survey on continual graph learning: https://arxiv.org/abs/2402.11565

We also maintain an up-to-date GitHub repository featuring a comprehensive list of CGL algorithms, accessible at https://github.com/UConn-DSIS/Survey-of-Continual-Learning-on-Graphs.

Other recommended works include:

  1. CGLB: Benchmark tasks for continual graph learning link
  2. Neural message passing for quantum chemistry link
  3. Continual lifelong learning with neural networks: A review link
  4. Three scenarios for continual learning link

Tutorial Outline

Most real-world graphs constantly grow or evolve with potential distribution shifts. Classical graph learning models, however, typically assume graphs to be static and suffer from catastrophic forgetting when new types of nodes and edges (or graphs) continuously emerge. Therefore, investigating how to constantly adapt a graph learning model to new distributions/tasks in the growing graphs without forgetting the previously learned knowledge, i.e. Continual Graph Learning (CGL), is becoming increasingly important in various real-world applications, e.g., social science, biomedical research, etc. Due to the existence of complex topological structures, CGL is essentially different from traditional continual learning on independent data without topological connections (e.g., images). Challenges in CGL include the task configuration in different types of graphs, preservation of the previously learned topology, properly handling the concept drift caused by the topological connections, etc. In this tutorial, we will introduce this newly emerging area - Continual Graph Learning (CGL). Specifically, we will (1) introduce different continual graph learning settings based on various application scenarios, (2) present the key challenges in CGL, (3) highlight the existing CGL techniques and benchmarks, and (4) discuss potential future directions.

Goal of the tutorial

Continual Graph Learning (CGL) investigates the graph learning problem in a highly practical scenario where the graphs are constantly growing or evolving, which is under-explored and is relevant to various artificial intelligence research directions, as well as tremendous real-world application scenarios (e.g., social science, biomedical research, etc). Therefore, our tutorial will not only attract interest from the audience with artificial intelligence, machine learning, and data mining background but also will attract interest from researchers focusing on specific applications, e.g., social networks, recommender systems, Internet of Things (IoT) networks, drug discovery, etc.

In this tutorial, we will introduce this newly emerging area - Continual Graph Learning (CGL). Specifically, we will (1) introduce different CGL settings based on various application scenarios, (2) present the key challenges in CGL, (3) highlight the existing CGL techniques and benchmarks, and (4) discuss potential future directions, as well as the relationship between CGL and various other research directions.

Tutors