arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.10480cs.LG
收藏

有监督动态图学习的编码器-解码器结构综述

Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey

McGill University(麦吉尔大学)

Yuecai Zhu, Fuyuan Lyu, Chengming Hu, Xi Chen, Xue Liu

摘要:

近年来,流行的在线服务产生了大量的用户活动数据。服务提供商收集这些数据,以便进行客户行为分析,并提供更好,更个性化的服务。这些数据中的大多数可以建模并存储为图,例如Facebook中的社交图,Youtube中的用户-视频交互图。这些图需要随着时间的推移而发展,以捕捉现实世界中的动态,从而导致动态图的发明。然而,嵌入在动态图的时态信息带来了新的挑战,分析和部署它们。事件陈旧、时间信息学习和显式时间维度使用是动态图学习中的一些示例挑战。为了给工业界和学术界提供一个方便的参考,本文提出了基于动态图进化理论的三阶段递归时态学习框架,以便用一个广义的框架来解释时态信息的学习。在这个框架下,本调查分类和审查不同的可学习的编码器-解码器架构的监督动态图学习。我们相信,这项调查可以提供有用的指导方针,研究人员和工程师在寻找合适的图形结构,为他们的动态学习任务。

英文摘要:

In recent years, the prevalent online services generate a sheer volume of user activity data. Service providers collect these data in order to perform client behavior analysis, and offer better and more customized services. Majority of these data can be modeled and stored as graph, such as the social graph in Facebook, user-video interaction graph in Youtube. These graphs need to evolve over time to capture the dynamics in the real world, leading to the invention of dynamic graphs. However, the temporal information embedded in the dynamic graphs brings new challenges in analyzing and deploying them. Events staleness, temporal information learning and explicit time dimension usage are some example challenges in dynamic graph learning. In order to offer a convenient reference to both the industry and academia, this survey presents the Three Stages Recurrent Temporal Learning Framework based on dynamic graph evolution theories, so as to interpret the learning of temporal information with a generalized framework. Under this framework, this survey categories and reviews different learnable encoder-decoder architectures for supervised dynamic graph learning. We believe that this survey could supply useful guidelines to researchers and engineers in finding suitable graph structures for their dynamic learning tasks.

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。

↑