{"html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fbuildersbox.corp-sansan.com%2Fentry%2F2020%2F10%2F12%2F110000\" title=\"Hands-on guidance to DGL library _ (4)  An introduction to training graph neural networks - Sansan Tech Blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","author_name":"sansanxingli","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/s/sansantech/20260224/20260224154704.png","provider_url":"https://hatena.blog","title":"Hands-on guidance to DGL library _ (4)  An introduction to training graph neural networks","author_url":"https://blog.hatena.ne.jp/sansanxingli/","height":"190","provider_name":"Hatena Blog","type":"rich","version":"1.0","published":"2020-10-12 11:00:00","blog_title":"Sansan Tech Blog","description":"Hi, I am XING LI, a researcher from Sansan DSOC. We have discussed some of the most important elements in DGL, such as Message Passing and NodeFlow. And we also explored a small but vital topic in most deep neural networks: (Negative) Sampling Methods. These are most of the tools we need to master f\u2026","categories":["R&D","\u9023\u8f09"],"blog_url":"https://buildersbox.corp-sansan.com/","url":"https://buildersbox.corp-sansan.com/entry/2020/10/12/110000","width":"100%"}