The task of item recommendation is to select the best items for a user from a large catalogue
of items. Item recommenders are commonly trained from implicit feedback which consists of …

Neural networks lack adversarial robustness, ie, they are vulnerable to adversarial
examples that through small perturbations to inputs cause incorrect predictions. Further, trust …

We study the problem of learning similarity functions over very large corpora using neural
network embedding models. These models are typically trained using SGD with sampling of …

Auxiliary information, such as reviews, have been widely adopted to improve collaborative
filtering (CF) algorithms, eg, to boost the accuracy and provide explanations. However, most …

Characterizing temporal dependence patterns is a critical step in understanding the
statistical properties of sequential data. Long Range Dependence (LRD)---referring to long …

It is crucial to model missing ratings in recommender systems since user preferences learnt
from only observed ratings are biased. One possible explanation for missing ratings is …

Many systems need to retrieve and score items from a huge catalog, such as recommender
and search ranking systems. We call this the deep retrieval problem. In this paper, we focus …

Recommender systems are widely used to recommend the most appealing items to users.
These recommendations can be generated by applying collaborative filtering methods. The …

In this thesis, we outline the research on the design of Domain Faithful Deep Learning
Systems, that translate expert-understandable domain knowledge and constraints to be …