Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems

Abstract

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.

KDD 2022, 11 pages, 12 figures, 5 tables

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• A Simple Framework for Contrastive Learning of Visual Representations
• Neural Message Passing for Quantum Chemistry
• Neural Graph Collaborative Filtering
• Learning deep representations by mutual information estimation and maximization
• Graph Convolutional Matrix Completion
• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
• What Makes for Good Views for Contrastive Learning?
• DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
• Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms
• AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction

Cited by in corpus (3)

• Multi-domain Recommendation with Embedding Disentangling and Domain Alignment
• Embedding Compression in Recommender Systems: A Survey
• Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation