Recurrent Neural Networks with Top-k Gains for Session-based Recommendations

  title={Recurrent Neural Networks with Top-k Gains for Session-based Recommendations},
  author={Bal{\'a}zs Hidasi and Alexandros Karatzoglou},
  journal={Proceedings of the 27th ACM International Conference on Information and Knowledge Management},
RNNs have been shown to be excellent models for sequential data and in particular for data that is generated by users in an session-based manner. [] Key Result We further demonstrate the performance gain of the RNN over baselines in an online A/B test.

Figures and Tables from this paper

Incorporating Dwell Time in Session-Based Recommendations with Recurrent Neural Networks

In its early stages, this research explores the value of incorporating dwell time into existing RNN framework for sessionbased recommendations by boosting items above the predefined dwell time threshold by evaluating the proposed approach on e-commerce RecSys’15 challenge dataset.

Data Augmentation Strategies for Improving Sequential Recommender Systems

This paper proposes a simple set of data augmentation strategies, all of which transform original item sequences in the way of direct corruption and describes howData augmentation changes the performance of sequential recommender systems.

Performance comparison of neural and non-neural approaches to session-based recommendation

An extensive set of experiments were conducted, using a variety of datasets, in which it turned out that simple techniques in most cases outperform recent neural approaches and point to certain major limitations of today's research practice.

Metric Learning for Session-based Recommendations

A simple architecture for problem analysis is proposed and it is demonstrated that neither extensively big nor deep architectures are necessary in order to outperform existing methods.

Contextual Hybrid Session-Based News Recommendation With Recurrent Neural Networks

This work presents a contextual hybrid, deep learning based approach for session-based news recommendation that is able to leverage a variety of information types and confirms the benefits of considering additional types of information, including article popularity and recency, in the proposed way.

Time-weighted Attentional Session-Aware Recommender System

This paper proposes ASARS, a novel framework that effectively imports the temporal dynamics methodology in CF into session-based RNN system in DL, such that the temporal info can act as scalable weights by a parallel attentional network.

A Study of Deep Learning-Based Approaches for Session-Based Recommendation Systems

There is still room for improving deep learning session-based recommendation algorithms by using various datasets and evaluation metrics to compare the performance of such algorithms.

Modeling Latent Autocorrelation for Session-based Recommendation

This paper proposes a novel and concise SBR model inspired by the basic concept of autocorrelation in the Stochastic Process that can learn better session preferences and is more efficient than most DNN-based models.

A Simple but Hard-to-Beat Baseline for Session-based Recommendations

A simple, but very effective generative model that is capable of learning high-level representation from both short- and long-range dependencies is proposed that attains state-of-the-art accuracy with less training time in the session-based recommendation task.



Improved Recurrent Neural Networks for Session-based Recommendations

This work proposes the application of two techniques to improve RNN-based models for session-based recommendations performance, namely, data augmentation, and a method to account for shifts in the input data distribution.

Session-based Recommendations with Recurrent Neural Networks

It is argued that by modeling the whole session, more accurate recommendations can be provided by an RNN-based approach for session-based recommendations, and introduced several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem.

Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations

It is shown that p-RNN architectures with proper training have significant performance improvements over feature-less session models while all session-based models outperform the item-to-item type baseline.

Recurrent Latent Variable Networks for Session-Based Recommendation

This work seeks to devise a machine learning mechanism capable of extracting subtle and complex underlying temporal dynamics in the observed session data, so as to inform the recommendation algorithm, by adopting concepts from the field of Bayesian statistics, namely variational inference.

Collaborative Filtering with Recurrent Neural Networks

It is shown that collaborative filtering can be viewed as a sequence prediction problem, and that given this interpretation, recurrent neural networks offer very competitive approach and the LSTM is competitive in all aspects.

CLiMF: learning to maximize reciprocal rank with collaborative less-is-more filtering

This paper proposes a new CF approach, Collaborative Less-is-More Filtering (CLiMF), where the model parameters are learned by directly maximizing the Mean Reciprocal Rank (MRR), which is a well-known information retrieval metric for measuring the performance of top-k recommendations.

Recurrent Recommender Networks

Recurrent Recommender Networks (RRN) are proposed that are able to predict future behavioral trajectories by endowing both users and movies with a Long Short-Term Memory (LSTM) autoregressive model that captures dynamics, in addition to a more traditional low-rank factorization.

BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies

It is shown that a carefully implemented version of BlackOut requires only 1-10 days on a single machine to train a RNNLM with a million word vocabulary and billions of parameters on one billion words, and can be used to any networks with large softmax output layers.

Fast ALS-based tensor factorization for context-aware recommendation from implicit feedback

Experiments performed on five implicit datasets show that by integrating context-aware information with the factorization framework into the state-of-the-art implicit recommender algorithm the recommendation quality improves significantly.

BPR: Bayesian Personalized Ranking from Implicit Feedback

This paper presents a generic optimization criterion BPR-Opt for personalized ranking that is the maximum posterior estimator derived from a Bayesian analysis of the problem and provides a generic learning algorithm for optimizing models with respect to B PR-Opt.