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.
Description
[1606.08117] Improved Recurrent Neural Networks for Session-based Recommendations
%0 Generic
%1 tan2016improved
%A Tan, Yong Kiam
%A Xu, Xinxing
%A Liu, Yong
%D 2016
%K embedding neural recommendation semantics
%T Improved Recurrent Neural Networks for Session-based Recommendations
%U http://arxiv.org/abs/1606.08117
%X 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.
@misc{tan2016improved,
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.},
added-at = {2017-01-09T11:06:29.000+0100},
author = {Tan, Yong Kiam and Xu, Xinxing and Liu, Yong},
biburl = {https://www.bibsonomy.org/bibtex/2e648099e4789eab294341ccb3e93b2c3/thoni},
description = {[1606.08117] Improved Recurrent Neural Networks for Session-based Recommendations},
interhash = {7dd7bde2439a64bdf01bac1202d701fd},
intrahash = {e648099e4789eab294341ccb3e93b2c3},
keywords = {embedding neural recommendation semantics},
note = {cite arxiv:1606.08117},
timestamp = {2017-01-09T11:06:29.000+0100},
title = {Improved Recurrent Neural Networks for Session-based Recommendations},
url = {http://arxiv.org/abs/1606.08117},
year = 2016
}