Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph

11/10/2020
by   Riku Togashi, et al.
0

Solving cold-start problems is indispensable to provide meaningful recommendation results for new users and items. Under sparsely observed data, unobserved user-item pairs are also a vital source for distilling latent users' information needs. Most present works leverage unobserved samples for extracting negative signals. However, such an optimisation strategy can lead to biased results toward already popular items by frequently handling new items as negative instances. In this study, we tackle the cold-start problems for new users/items by appropriately leveraging unobserved samples. We propose a knowledge graph (KG)-aware recommender based on graph neural networks, which augments labelled samples through pseudo-labelling. Our approach aggressively employs unobserved samples as positive instances and brings new items into the spotlight. To avoid exhaustive label assignments to all possible pairs of users and items, we exploit a KG for selecting probably positive items for each user. We also utilise an improved negative sampling strategy and thereby suppress the exacerbation of popularity biases. Through experiments, we demonstrate that our approach achieves improvements over the state-of-the-art KG-aware recommenders in a variety of scenarios; in particular, our methodology successfully improves recommendation performance for cold-start users/items.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/12/2020

Reinforced Negative Sampling over Knowledge Graph for Recommendation

Properly handling missing data is a fundamental challenge in recommendat...
research
05/11/2019

Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems

Knowledge graphs capture structured information and relations between a ...
research
08/11/2022

Task Aligned Meta-learning based Augmented Graph for Cold-Start Recommendation

The cold-start problem is a long-standing challenge in recommender syste...
research
07/07/2021

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

Collaborative filtering (CF) is widely used to learn an informative late...
research
05/11/2019

Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommendation

Knowledge graphs capture structured information and relations between a ...
research
11/16/2020

SamWalker++: recommendation with informative sampling strategy

Recommendation from implicit feedback is a highly challenging task due t...
research
07/13/2018

Computing recommendations via a Knowledge Graph-aware Autoencoder

In the last years, deep learning has shown to be a game-changing technol...

Please sign up or login with your details

Forgot password? Click here to reset