Recommender systems usually amplify the biases in the data. The model learned from
historical interactions with imbalanced item distribution will amplify the imbalance by over …

Modern recommender systems learn user representations from historical interactions, which
suffer from the problem of user feature shifts, such as an income increase. Historical …

Graph Neural Networks (GNNs) are proposed without considering the agnostic distribution
shifts between training graphs and testing graphs, inducing the degeneration of the …

Deep candidate generation (DCG) that narrows down the collection of relevant items from
billions to hundreds via representation learning has become prevalent in industrial …

Causality lays the foundation for the trajectory of our world. Causal inference (CI), which
aims to infer intrinsic causal relations among variables of interest, has emerged as a crucial …

Recommender systems usually face the issue of filter bubbles: over-recommending
homogeneous items based on user features and historical interactions. Filter bubbles will …

Data-driven recommender systems have demonstrated great success in various Web
applications owing to the extraordinary ability of machine learning models to recognize …

Recommender systems easily face the issue of user preference shifts. User representations
will become out-of-date and lead to inappropriate recommendations if user preference has …

This invited Review discusses causal learning in the context of robotic intelligence. The
Review introduces the psychological findings on causal learning in human cognition, as well …

Offline policy evaluation (OPE) aims to accurately estimate the performance of a hypothetical
policy using only historical data, which has drawn increasing attention in a wide range of …