Detecting Beneficial Feature Interactions for Recommender Systems
arXiv:2008.00404
Abstract
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 interactions may not be that relevant to the recommendation result, and taking them into account may introduce noise and decrease recommendation accuracy. To make the best out of feature interactions, we propose a graph neural network approach to effectively model them, together with a novel technique to automatically detect those feature interactions that are beneficial in terms of recommendation accuracy. The automatic feature interaction detection is achieved via edge prediction with an L0 activation regularization. Our proposed model is proved to be effective through the information bottleneck principle and statistical interaction theory. Experimental results show that our model (i) outperforms existing baselines in terms of accuracy, and (ii) automatically identifies beneficial feature interactions.
14 pages, 7 figures, 5 tables, AAAI 2021
References in corpus (5)
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- A Compositional Object-Based Approach to Learning Physical Dynamics
- Frappe: Understanding the Usage and Perception of Mobile App Recommendations In-The-Wild
- Revisiting Activation Regularization for Language RNNs
- Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms
Cited by in corpus (4)
- Graph Pooling via Coarsened Graph Infomax
- Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction
- JEPOO: Highly Accurate Joint Estimation of Pitch, Onset and Offset for Music Information Retrieval
- Intrinsic and Extrinsic Factor Disentanglement for Recommendation in Various Context Scenarios