Empirical Comparison of Graph Embeddings for Trust-Based Collaborative Filtering
This work addresses the problem of improving recommendation systems for users in cold-start settings, but it is incremental as it empirically compares existing methods.
The study compared graph embedding methods for trust-based collaborative filtering in cold-start scenarios, finding that random-walk-based approaches consistently achieved the best accuracy and improved user coverage across three datasets.
In this work, we study the utility of graph embeddings to generate latent user representations for trust-based collaborative filtering. In a cold-start setting, on three publicly available datasets, we evaluate approaches from four method families: (i) factorization-based, (ii) random walk-based, (iii) deep learning-based, and (iv) the Large-scale Information Network Embedding (LINE) approach. We find that across the four families, random-walk-based approaches consistently achieve the best accuracy. Besides, they result in highly novel and diverse recommendations. Furthermore, our results show that the use of graph embeddings in trust-based collaborative filtering significantly improves user coverage.