Exploiting Co-occurrence for Implicit Feedback Recommendation

PhD Thesis Defence


Title: "Exploiting Co-occurrence for Implicit Feedback Recommendation"

By

Mr. Farhan KHAWAR


Abstract

Recommender systems serve as bridges between users and items by recommending 
items to users that they might find interesting. Collaborative filtering (CF) 
is a technique commonly used in recommender systems. It predicts a user's 
preference for an item based on past user-item interactions. A common form of 
this past interaction is called implicit feedback in which we record the user 
consumption behavior (click/buy/watch etc.) when they interact with items. The 
simplicity of implicit feedback brings the challenge of the sparseness of the 
signal. Specifically, it is positive-only feedback since it only contains the 
positive signal of a user consuming an item. With such data, a valuable piece 
of information that can be used for making recommendations is the co-occurrence 
of items or users; that is, two items being co-consumed by users or two users 
co-consuming the same item.

In this thesis, we explore the role of co-occurrence in implicit feedback 
recommendation. In the first part, we show that efficient co-occurrence 
estimation can lead to improved recommendations by two popular recommenders. We 
show that the memory-based recommenders rely on co-occurrence estimation but 
due to the finite sample size, this estimation is noisy. Using insights from 
Marchenko-Pastur law we remove this noise by clipping small eigenvalues of the 
co-occurrence matrix. Also, we can shrink the largest eigenvalue to remove the 
"global" effects of the system. Both these cleaning strategies lead to better 
co-occurrence estimation, and this is translated into more accurate and diverse 
recommendations.

In the second part, we introduce methods that further exploit the co-occurrence 
information by building models on top of the item co-occurrence. We introduce 
the notion of multi-dimensional user clustering, where each dimension is a 
group of co-occurring items. We present two methods to perform this 
multi-dimensional user clustering. Unlike existing latent vector methods, the 
resulting models learn interpretable latent dimensions that lend themselves 
easily for explanations. In addition, they exhibit a better warm and cold start 
performance.

In the third part, we introduce structure learning for deep learning based 
implicit feedback recommenders. We use the item co-occurrence to learn the 
structure of auto-encoder based recommenders. The resulting sparse structure 
can be seen as a structural prior for network training and it guides the 
parameter estimation. This leads to improved performance over the 
state-of-the-art deep learning based recommenders due to a smaller spectral 
norm of the weight matrices and hence a better generalization performance.

Finally, we explore the case when additional features information is also 
available with implicit feedback. When a user consumes an item we can treat 
their features as co-occurring. However, the existing methods model all feature 
co-occurrence. Moreover, they model each of these feature co-occurrences using 
the same function. We propose a neural architecture search based approach to 
search for which feature interactions to model and how to model these 
interactions. The results show that this approach outperforms the 
state-of-the-art feature interaction based recommenders using a fraction of the 
parameters and flops and it learns meaningful feature co-occurrences.


Date:			Wednesday, 15 January 2020

Time:			3:00pm - 5:00pm

Venue:			Room 3494
 			Lifts 25/26

Chairman:		Prof. Jianfeng CAI (MATH)

Committee Members:	Prof. Nevin ZHANG (Supervisor)
 			Prof. Fangzhen LIN
 			Prof. Raymond Wong
 			Prof. Bing-yi JING (MATH)
 			Prof. William Kwok-Wai CHEUNG (Baptist University)


**** ALL are Welcome ****