Deep Models of Interactions Across Sets

ICML 2018 Jason HartfordDevon R GrahamKevin Leyton-BrownSiamak Ravanbakhsh

We use deep learning to model interactions across two or more sets of objects, such as user-movie ratings, protein-drug bindings, or ternary user-item-tag interactions. The canonical representation of such interactions is a matrix (or a higher-dimensional tensor) with an exchangeability property: the encoding's meaning is not changed by permuting rows or columns... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Collaborative Filtering Douban Factorized Exchangeable Autoencoder RMSE 0.738 # 4
Collaborative Filtering Flixster Factorized Exchangeable Autoencoder RMSE 0.908 # 1
Collaborative Filtering MovieLens 100K Self-Supervised Exchangeable Model RMSE 0.91 # 2
Collaborative Filtering YahooMusic Factorized Exchangeable Autoencoder RMSE 20.0 # 1