Fusion Strategies for Learning User Embeddings with Neural Networks
P. Blandfort, T. Karayil, F. Raue, J. Hees, A. Dengel
Abstract
We analyze the effect on embedding quality caused by several fusion strategies in neural networks for learning user embeddings from rating data. We propose Pair-Distance Correlation, a novel measure for evaluating embedding quality, and find that prediction performance not necessarily reflects embedding quality.
Abstract
Growing amounts of online user data motivate the need for automated processing techniques. In case of user ratings, one interesting option is to use neural networks for learning to predict ratings given an item and a user. While training for prediction, such an approach at the same time learns to map each user to a vector, a so-called user embedding.
Key Findings
In this paper, we run an experiment on movie ratings data, where we analyze the effect on embedding quality caused by several fusion strategies in neural networks. For evaluating embedding quality, we propose a novel measure, Pair-Distance Correlation, which quantifies the condition that similar users should have similar embedding vectors.
We find that the fusion strategy affects results in terms of both prediction performance and embedding quality. Surprisingly, we find that prediction performance not necessarily reflects embedding quality. This suggests that if embeddings are of interest, the common tendency to select models based on their prediction ability should be reconsidered.