Augmenting the User-Item Graph with Textual Similarity Models
arXiv:2109.09358
Abstract
This paper introduces a simple and effective form of data augmentation for recommender systems. A paraphrase similarity model is applied to widely available textual data, such as reviews and product descriptions, yielding new semantic relations that are added to the user-item graph. This increases the density of the graph without needing further labeled data. The data augmentation is evaluated on a variety of recommendation algorithms, using Euclidean, hyperbolic, and complex spaces, and over three categories of Amazon product reviews with differing characteristics. Results show that the data augmentation technique provides significant improvements to all types of models, with the most pronounced gains for knowledge graph-based recommenders, particularly in cold-start settings, leading to state-of-the-art performance.
arXiv comment12 pages, 2 figures
References in corpus (23)
- Geometric deep learning: going beyond Euclidean data
- An Overview of Multi-Task Learning in Deep Neural Networks
- KGAT: Knowledge Graph Attention Network for Recommendation
- Convolutional Neural Networks for Sentence Classification
- Complex Embeddings for Simple Link Prediction
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
- Learning over Knowledge-Base Embeddings for Recommendation
- Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
- Translation-based Recommendation
- TransNets: Learning to Transform for Recommendation
- Quaternion Knowledge Graph Embeddings
- Representation Tradeoffs for Hyperbolic Embeddings
- Data augmentation instead of explicit regularization
- Inferring Networks of Substitutable and Complementary Products
- Improved Recurrent Neural Networks for Session-based Recommendations
- How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements
- Canonical Tensor Decomposition for Knowledge Base Completion
- Hyperbolic Neural Networks
- Latent geometry of bipartite networks
- Skip-gram word embeddings in hyperbolic space
- Ricci Curvature of the Internet Topology
- Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach