Graph learning substantially contributes to solving artificial intelligence (AI) tasks in various graph-related domains such as social networks, biological networks, recommender systems, and computer vision. However, despite its unprecedented prevalence, addressing the dynamic evolution of graph data over time remains a challenge. In many real-world applications, graph data continuously evolves. Current graph learning methods that assume graph representation is complete before the training process begins are not applicable in this setting. This challenge in graph learning motivates the development of a continuous learning process called graph lifelong learning to accommodate the future and refine the previous knowledge in graph data. Unlike existing survey papers that focus on either lifelong learning or graph learning separately, this survey paper covers the motivations, potentials, state-of-the-art approaches (that are well categorized), and open issues of graph lifelong learning. We expect extensive research and development interest in this emerging field.
翻译:图表学习在很大程度上有助于解决社会网络、生物网络、推荐人系统、计算机愿景等与图表有关的各个领域的人工智能(AI)任务。然而,尽管其规模前所未有,但处理图表数据随时间推移的动态演变仍然是一个挑战。在许多现实应用中,图表数据在不断演变。目前图表学习方法假定图示在培训过程开始前完成,但在此背景下并不适用。图形学习的这项挑战激励着持续学习进程的发展,称为图示终身学习,以适应未来,并完善图表数据中先前的知识。与现有的侧重于终身学习或图表学习的调查报告不同,本调查文件涵盖了动机、潜力、最新方法(分类良好)以及图示终身学习的开放问题。我们期望在这一新兴领域进行广泛的研究和开发。