ACM SIGMOD Record ( IF 1.1 ) Pub Date : 2022-06-01 , DOI: 10.1145/3542700.3542710 Aidan Hogan 1
The machine learning community has traditionally been proactive in developing techniques for diverse types of data, such as text, audio, images, videos, time series, and, of course, matrices, tensors, etc. "But what about graphs?" some of us graph enthusiasts may have asked ourselves, dejectedly, before transforming our beautiful graph into a brutalistic table of numbers that bore little resemblance to its parent, nor the phenomena it represented, but could at least be shovelled into the machine learning frameworks of the time. Thankfully those days are coming to an end.
中文翻译:
技术视角 - 没有窗格,没有增益:在单个服务器中扩展属性网络嵌入:ACM SIGMOD 记录:第 51 卷,第 1 期
传统上,机器学习社区一直积极地为各种类型的数据开发技术,例如文本、音频、图像、视频、时间序列,当然还有矩阵、张量等。“但是图形呢?” 我们中的一些图表爱好者可能会沮丧地问自己,在将我们美丽的图表转换成一张野蛮的数字表之前,这些数字与它的父级几乎没有相似之处,也与它所代表的现象几乎没有相似之处,但至少可以被塞进机器学习框架中。时间。谢天谢地,那些日子即将结束。