Collaborative Memory Network for Recommendation Systems
Abstract
Recommendation systems play a vital role to keep users engaged
with personalized content in modern online platforms. Deep learning
has revolutionized many research fields and collaborative filtering
(CF) is no different. However, existing methods compose deep
learning architectures with the latent factor model ignoring a major
class of CF models, neighborhood or memory-based approaches.
We propose Collaborative Memory Networks (CMN), a deep architecture
to unify the two classes of CF models capitalizing on the
strengths of the global structure of latent factor model and local
neighborhood-based structure in a nonlinear fashion. Motivated by
the success of Memory Networks, we fuse a memory component
and neural attention mechanism as the neighborhood component.
The associative addressing scheme with the user and item memories
in the memory module encodes complex user-item relations
coupled with the neural attention mechanism to learn a user-item
specific neighborhood. Finally, the output module jointly exploits
the neighborhood with the user and item memories to produce the
final ranking score. Stacking multiple memory modules together
yielding deeper architectures capturing additional complex useritem
relations. Furthermore, we show strong connections between
CMN components and two classes of CF models. Comprehensive
experimental results demonstrate the effectiveness of CMN on two
public datasets outperforming competitive baselines. Qualitative visualization
of the attention weights provide insight into the model’s
recommendation process and suggest the presence of higher order
interactions.