An efficient manifold density estimator for all recommendation systems

Many unsupervised representation learning methods belong to the class of similarity learning models. While various modality-specific approaches exist for different types of data, a core property of many methods is that representations of similar inputs are close under some similarity function. We propose EMDE (Efficient Manifold Density Estimator) - a framework utilizing arbitrary vector representations with the property of local similarity to succinctly represent smooth probability densities on Riemannian manifolds. Our approximate representation has the desirable properties of being fixed-size and having simple additive compositionality, thus being especially amenable to treatment with neural networks - both as input and output format, producing efficient conditional estimators. We generalize and reformulate the problem of multi-modal recommendations as conditional, weighted density estimation on manifolds. Our approach allows for trivial inclusion of multiple interaction types, modalities of data as well as interaction strengths for any recommendation setting. Applying EMDE to both top-k and session-based recommendation settings, we establish new state-of-the-art results on multiple open datasets in both uni-modal and multi-modal settings.

PDF Abstract

Results from the Paper

 Ranked #1 on Session-Based Recommendations on yoochoose1 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Session-Based Recommendations Diginetica EMDE MRR@20 17.24 # 11
Hit@20 37.52 # 12
Session-Based Recommendations Diginetica EMDE MM MRR@20 17.31 # 10
Hit@20 38.49 # 11
Session-Based Recommendations Retailrocket EMDE MM MRR@20 0.3664 # 1
Hit@20 0.5073 # 1
Session-Based Recommendations Retailrocket EMDE MRR@20 0.3524 # 2
Hit@20 0.4704 # 2
Session-Based Recommendations yoochoose1 EMDE MM MRR@20 31.16 # 1
Precision@20 74.3 # 1
Session-Based Recommendations yoochoose1 EMDE MRR@20 31.04 # 3
Precision@20 73.0 # 2


No methods listed for this paper. Add relevant methods here