Improved Recurrent Neural Networks for Session-based Recommendations

Abstract

Recurrent neural networks (RNNs) were recently proposed for the session-based recommendation task. The models showed promising improvements over traditional recommendation approaches. In this work, we further study RNN-based models for session-based recommendations. We propose the application of two techniques to improve model performance, namely, data augmentation, and a method to account for shifts in the input data distribution. We also empirically study the use of generalised distillation, and a novel alternative model that directly predicts item embeddings. Experiments on the RecSys Challenge 2015 dataset demonstrate relative improvements of 12.8% and 14.8% over previously reported results on the Recall@20 and Mean Reciprocal Rank@20 metrics respectively.

References in corpus (6)

• Distilling the Knowledge in a Neural Network
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Deep Residual Learning for Image Recognition
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• Transfer Hashing with Privileged Information

Cited by in corpus (22)

• Deep Coevolutionary Network: Embedding User and Item Features for Recommendation
• Variational Autoencoders for Collaborative Filtering
• Predicting purchasing intent: Automatic Feature Learning using Recurrent Neural Networks
• Temporal Learning and Sequence Modeling for a Job Recommender System
• Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks
• Large-Scale User Modeling with Recurrent Neural Networks for Music Discovery on Multiple Time Scales
• Improving Session Recommendation with Recurrent Neural Networks by Exploiting Dwell Time
• Time is of the Essence: a Joint Hierarchical RNN and Point Process Model for Time and Item Predictions
• Recurrent Latent Variable Networks for Session-Based Recommendation
• Modelling Sequential Music Track Skips using a Multi-RNN Approach
• Attention-based Mixture Density Recurrent Networks for History-based Recommendation
• A Simple Convolutional Generative Network for Next Item Recommendation
• Memory Augmented Neural Model for Incremental Session-based Recommendation
• Future-Aware Diverse Trends Framework for Recommendation
• SeER: An Explainable Deep Learning MIDI-based Hybrid Song Recommender System
• Augmenting the User-Item Graph with Textual Similarity Models
• Deep Reinforcement Learning for Personalized Search Story Recommendation
• LSTM Networks for Online Cross-Network Recommendations
• A collaborative filtering model with heterogeneous neural networks for recommender systems
• Context-aware short-term interest first model for session-based recommendation
• Breaking the Softmax Bottleneck for Sequential Recommender Systems with Dropout and Decoupling
• Sequential Variational Autoencoders for Collaborative Filtering