On the instability of embeddings for recommender systems

Abstract

Most state-of-the-art top-N collaborative recommender systems work by learning embeddings to jointly represent users and items. Learned embeddings are considered to be effective to solve a variety of tasks. Among others, providing and explaining recommendations. In this paper we question the reliability of the embeddings learned by Matrix Factorization (MF). We empirically demonstrate that, by simply changing the initial values assigned to the latent factors, the same MF method generates very different embeddings of items and users, and we highlight that this effect is stronger for less popular items. To overcome these drawbacks, we present a generalization of MF, called Nearest Neighbors Matrix Factorization (NNMF). The new method propagates the information about items and users to their neighbors, speeding up the training procedure and extending the amount of information that supports recommendations and representations. We describe the NNMF variants of three common MF approaches, and with extensive experiments on five different datasets we show that they strongly mitigate the instability issues of the original MF versions and they improve the accuracy of recommendations on the long-tail.

Modeling walkability by remote sensing as latent walking speed extracted from multiple digital trail maps

“…The calculated factors are used for prediction of ratings of known users for known items and for filling the sparse matrix A with unknown values. However, the algorithm we used was critiqued by [18] for its instability, mostly due to a phenomenon called 'popularity bias' where popular items are rated more often, while unpopular items are rarely rated. However, due to the nature of our dataset, we can plausibly excluded the popularity bias.…”

Makine Öğrenimi ile Uzun Kuyruk Ürünler için İyileştirilmiş Sonraki Öğe Önerisi

“…Tavsiyeleri ve temsilleri destekleyen bilgi miktarını genişletmek için yaygın MF yaklaşımının NNMF varyantlarını tanımlanmıştır. Beş farklı veri kümesi üzerinde kapsamlı deneyler gerçekleştirilmiştir [22].…”