search

jasperzhong / read-papers-and-code

My paper/code reading notes in Chinese
43 stars 3 forks source link

KDD '21 | Multi-view Denoising Graph Auto-Encoders on Heterogeneous Information Networks for Cold-start Recommendation #376

Closed jasperzhong closed 9 months ago

jasperzhong commented 9 months ago

http://184pc128.csie.ntnu.edu.tw/presentation/21-11-09/Multi-view%20Denoising%20Graph%20Auto-Encoders%20on%20Heterogeneous.pdf

jasperzhong commented 9 months ago

PlatoGL用的模型叫MvDGAE，也是一个heterogeneous GNN. 感觉和HAN #328 差不多，也是每个metapath-based (second-order proximity)有一个graph encoder，然后把每个relation的output embedding aggregate. 不过它为了解决冷启动问题，多了个decoder，随机drop掉一些user-item然后做预测算一个loss加进去一起训练.

image

里面有一个sampling过程. 比如上图有UUI, UIU两个metapath，每个hop都sample若干个neighbors. 在PlatoGL里面每个hop sample 50个neighbors.

jasperzhong commented 9 months ago

PlatoGL里面用到的metapath很多: