Forest-based Deep Recommender

With the development of deep learning techniques, deep recommendation models also achieve remarkable improvements in terms of recommendation accuracy. However, due to the large number of candidate items in practice and the high cost of preference computation, these methods also suffer from low efficiency of recommendation. The recently proposed tree-based deep recommendation models alleviate the problem by directly learning tree structure and representations under the guidance of recommendation objectives. However, such models have two shortcomings. First, the max-heap assumption in the hierarchical tree, in which the preference for a parent node should be the maximum between the preferences for its children, is difficult to satisfy in their binary classification objectives. Second, the learned index only includes a single tree, which is different from the widely-used multiple trees index, providing an opportunity to improve the accuracy of recommendation. To this end, we propose a Deep Forest-based Recommender (DeFoRec for short) for an efficient recommendation. In DeFoRec, all the trees generated during training process are retained to form the forest. When learning node representation of each tree, we have to satisfy the max-heap assumption as much as possible and mimic beam search behavior over the tree in the training stage. This is achieved by DeFoRec to regard the training task as multiclassification over tree nodes at the same level. However, the number of tree nodes grows exponentially with levels, making us to train the preference model by the guidance of sampled-softmax technique. The experiments are conducted on real-world datasets, validating the effectiveness of the proposed preference model learning method and tree learning method.