Detecting Beneficial Feature Interactions for Recommender Systems

Feature interactions are essential for achieving high accuracy in recommender systems. Many studies take into account the interaction between every pair of features. However, this is suboptimal because some feature may not be that relevant to recommendation result and taking them introduce noise decrease accuracy. To make best out interactions, we propose a graph neural network approach effectively model them, together with novel technique automatically detect those beneficial terms The automatic detection achieved via edge prediction an L0 activation regularization. Our proposed proved effective through information bottleneck principle statistical theory. Experimental results show our (i) outperforms existing baselines accuracy, (ii) identifies interactions.