arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.11750cs.LGcs.AI
收藏

深度图网络中的灾难性遗忘:图分类的入门基准

Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification

University of Pisa(比萨大学);Scuola Normale Superiore(高等师范学院)

Antonio Carta, Andrea Cossu, Federico Errica, Davide Bacciu

摘要:

在这项工作中,我们研究了图表示学习场景中的灾难性遗忘现象。分析的主要目的是了解经典的持续学习技术,平面和顺序数据有一个有形的影响性能时,应用于图形数据。为此,我们在三个不同的数据集上,在鲁棒和受控的环境中,使用结构不可知模型和深度图网络进行了实验。该基准的补充调查结构保持正则化技术对灾难性遗忘的影响。我们发现,重放是迄今为止最有效的策略,这也是最受益于正则化的使用。我们的研究结果表明,有趣的未来研究的交叉点的连续和图形表示学习领域。最后,我们为研究人员提供了一个灵活的软件框架来重现我们的结果,并进行进一步的实验。

英文摘要:

In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether classical continual learning techniques for flat and sequential data have a tangible impact on performances when applied to graph data. To do so, we experiment with a structure-agnostic model and a deep graph network in a robust and controlled environment on three different datasets. The benchmark is complemented by an investigation on the effect of structure-preserving regularization techniques on catastrophic forgetting. We find that replay is the most effective strategy in so far, which also benefits the most from the use of regularization. Our findings suggest interesting future research at the intersection of the continual and graph representation learning fields. Finally, we provide researchers with a flexible software framework to reproduce our results and carry out further experiments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑