Enhancing Factorization Machines with Generalized Metric Learning
Authors:
- Yangyang GuoYGYangyang Guo
- Zhiyong ChengZCZhiyong Cheng
- Jiazheng JingJJJiazheng Jing
- Yanpeng LinYLYanpeng Lin
- Liqiang NieLNLiqiang Nie
- Meng WangMWMeng Wang
Preprint
Abstract
Factorization Machines (FMs) are effective in incorporating side information to overcome the cold-start and data sparsity problems in recommender systems. Traditional FMs adopt the inner product to model the second-order interactions between different attributes, which are represented via feature vectors. The problem is that the inner product violates the triangle inequality property of feature vectors. As a result, it cannot well capture fine-grained attribute interactions, resulting in sub-optimal performance. Recently, the Euclidean distance is exploited in FMs to replace the inner product and has delivered better performance. However, previous FM methods including the ones equipped with the Euclidean distance all focus on the attribute-level interaction modeling, ignoring the critical intrinsic feature correlations inside attributes. Thereby, they fail to model the complex and rich interactions exhibited in the real-world data. To tackle this problem, in this paper, we propose a FM framework equipped with generalized metric learning techniques to better capture these feature correlations. In particular, based on this framework, we present a Mahalanobis distance and a deep neural network (DNN) methods, which can effectively model the linear and non-linear correlations between features, respectively. Besides, we design an efficient approach for simplifying the model functions. Experiments on several benchmark datasets demonstrate that our proposed framework outperforms several state-of-the-art baselines by a large margin. Moreover, we collect a new large-scale dataset on second-hand trading to justify the effectiveness of our method over cold-start and data sparsity problems in recommender systems.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- HiTR: Hierarchical Topic Model Re-Estimation for Measuring Topical Diversity of DocumentsIEEE Transactions on Knowledge and Data Engineering, 2018
- Efficient Multi-Class Probabilistic SVMs on GPUsIEEE Transactions on Knowledge and Data Engineering, 2018
- Correlated Matrix Factorization for Recommendation with Implicit FeedbackIEEE Transactions on Knowledge and Data Engineering, 2018
- Addressing Interpretability and Cold-Start in Matrix Factorization for Recommender SystemsIEEE Transactions on Knowledge and Data Engineering, 2018
- Scalable Content-Aware Collaborative Filtering for Location RecommendationIEEE Transactions on Knowledge and Data Engineering, 2018
- Gradient boosting factorization machines2014
- Speeding up the Xbox recommender system using a euclidean transformation for inner-product spaces2014
- Fast context-aware recommendations with factorization machines2011
- Factorizing personalized Markov chains for next-basket recommendation2010
- Pairwise interaction tensor factorization for personalized tag recommendation2010