Kostadin Georgiev, VMware BulgariaPreslav Nakov, Qatar Computing Research Institute

ICML, June 17, 2013, Atlanta

6. Comparison to Previous Work

1. Overview

A NON-IID FRAMEWORKFOR COLLABORATIVE FILTERING WITH RESTRICTED BOLTZMANN MACHINES

5. Experiments & Evaluation

• We propose a non-IID framework for collaborative filtering

• based on Restricted Boltzmann Machines (RBM)

• models both user-user and item-item correlations

• uses real values in the visible layer (as opposed to multinomial) to model user-item ratings, thus taking advantage of the natural order between them

• We further explore the potential of combining the original training data with data generated by the RBM-based model itself in a bootstrapping fashion

• Evaluation: on two MovieLens datasets - with 100K and 1M user-item ratings, respectively

• Results: Rival the state-of-the-art

2. User/Item-based RBM Model

7. Conclusion & Future Work

• Conclusion

• proposed a non-IID RBM framework for collaborative filtering

• rivals the best previous algorithms, which are more complex

3. Non-IID Hybrid RBM Model

MovieLens 100kMovieLens 1M

• The visible layer• represents either all ratings by a user or all rating for an item

• units model ratings as real values (vs. multinomial)

• noise-free reconstruction is better

• Remove the IID assumption for the training data

• Topology: Unit vij is connected to two independent hidden layers: one user-based and another item-based.

• Missing values (ratings): the generated predictions are used during testing, but are ignored during training

• Training procedure: we average the predictions of the user-based and of the item-based RBM models

4. Neighborhood + I-RBM

Use the I-RBM predictions from a neighborhood-based algorithm:

However, compute the averages from the original ratings:• Future work

• add an additional layer to model higher-order correlations

• add content-based features, e.g., demographic

• Two MovieLens datasets:• 100k:

• 1,682 movies assigned

• 943 users

• 100,000 ratings

• sparseness: 93.7%

• Each rating is between 1 (worst) and 5 (best)

Data

• 1M:

• 3,952 movies

• 6,040 users

• 1 million ratings

• sparseness: 95.8%

- Item-based RBM model outperforms user-based, but not by much.- Hybrid item-based RBM + NB model is relatively insensitive to number of units.

In the IID case, multinomial visible units are better than real-valued. In the non-IID case: real-valued visible units outperform multinomial.

• Mean Absolute Error (MAE):

• Cross-validation• 5-fold

• 80%:20% training:testing data splits

Evaluation