Detecting Relevant Feature Interactions for Recommender Systems via Graph Neural Networks.
Year: 2020
Type: preprint
Abstract: Feature interactions are essential for achieving high accuracy in recommendersystems (RS), so they have been taken into consideration in many existing RS,
where all feature interactions are modeled. Nevertheless, not all feature
interactions have positive effects for RS: modeling the irrelevant feature
interactions may introduce noises and degrade the accuracy. To overcome this
problem, in this work, we propose a graph neural network-based model, L0-SIGN,
to detect the relevance of feature interactions and utilize only the relevant
ones for RS, with features as nodes and feature interactions as edges.
Generally, our model consists of two components: an L0 regularization based
edge prediction model to explicitly detect relevant feature interactions; and a
graph classification model, SIGN, to effectively model and aggregate the
detected ones for recommendations. These two components positively influence
each other to ensure that the most relevant feature interactions will be
detected and modeled. In addition, we further prove that the effectiveness of
our model is theoretically sound. We first show that our model is a variational
approximation of information bottleneck principle, i.e., the detected feature
interactions are guaranteed to be most relevant. We then show that our model
follows the definition of statistical interactions, proving that the modeling
of detected feature interactions in L0-SIGN is effective. Experimental results
show that (i) L0-SIGN outperforms existing baselines in terms of accuracy, and
(ii) the detected feature interactions are beneficial for performance gain and
interpretability.
Source: arXiv (Cornell University)
Authors: Yixin Su, Rui Zhang, Sarah M. Erfani, Zhenghua Xu
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3046571202