Robust generalization aims to tackle the most challenging data distributions which are rare
in the training set and contain severe noises, ie, photon-limited corruptions. Common …

This paper offers a new perspective to ease the challenge of domain generalization, which
involves maintaining robust results even in unseen environments. Our design focuses on the …

We present a new zero-shot dense retrieval (ZeroDR) method, COCO-DR, to improve the
generalization ability of dense retrieval by combating the distribution shifts between source …

Subpopulation shift widely exists in many real-world machine learning applications, referring
to the training and test distributions containing the same subpopulation groups but varying in …

While machine learning models rapidly advance the state-of-the-art on various real-world
tasks, out-of-domain (OOD) generalization remains a challenging problem given the …

Collaborative Filtering (CF) recommender models highly depend on user-item interactions to
learn CF representations, thus falling short of recommending cold-start items. To address …

Click-Through Rate (CTR) prediction plays a core role in recommender systems, serving as
the final-stage filter to rank items for a user. The key to addressing the CTR task is learning …

Collaborative Filtering (CF) has been widely applied for personalized recommendations in
various industrial applications. However, due to the training strategy of Empirical Risk …

Fairness of recommender systems (RS) has attracted increasing attention recently. Based
on the involved stakeholders, the fairness of RS can be divided into user fairness, item …

Training Graph Neural Networks (GNNs) on large-scale graphs in the deep learning era can
be expensive. While graph condensation has recently emerged as a promising approach …