Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
This addresses a key computational bottleneck in recommender systems for improving accuracy, though it is an incremental advance over prior limited-order methods.
The paper tackles the problem of detecting beneficial feature interactions of arbitrary orders in recommender systems, which is computationally prohibitive for existing methods, and proposes HIRS, a hypergraph neural network model that directly generates such interactions, achieving up to 5% improvement in recommendation accuracy.
Detecting beneficial feature interactions is essential in recommender systems, and existing approaches achieve this by examining all the possible feature interactions. However, the cost of examining all the possible higher-order feature interactions is prohibitive (exponentially growing with the order increasing). Hence existing approaches only detect limited order (e.g., combinations of up to four features) beneficial feature interactions, which may miss beneficial feature interactions with orders higher than the limitation. In this paper, we propose a hypergraph neural network based model named HIRS. HIRS is the first work that directly generates beneficial feature interactions of arbitrary orders and makes recommendation predictions accordingly. The number of generated feature interactions can be specified to be much smaller than the number of all the possible interactions and hence, our model admits a much lower running time. To achieve an effective algorithm, we exploit three properties of beneficial feature interactions, and propose deep-infomax-based methods to guide the interaction generation. Our experimental results show that HIRS outperforms state-of-the-art algorithms by up to 5% in terms of recommendation accuracy.