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

By Balázs Hidasi, Domonkos Tikk. 2012

152 citations recorded by the source corpus.

Albeit the implicit feedback based recommendation problem--when only the user history is available but there are no ratings--is the most typical setting in real-world applications, it is much less researched than the explicit feedback case. State-of-the-art algorithms that are efficient on the explicit case cannot be straightforwardly transformed to the implicit case if scalability should be maintained. There are few implicit feedback benchmark datasets, therefore new ideas are usually experimented on explicit benchmarks. In this paper, we propose a generic context-aware implicit feedback recommender algorithm, coined iTALS. iTALS applies a fast, ALS-based tensor factorization learning method that scales linearly with the number of non-zero elements in the tensor. The method also allows us to incorporate various contextual information into the model while maintaining its computational efficiency. We present two context-aware implementation variants of iTALS. The first incorporates seasonality and enables to distinguish user behavior in different time intervals. The other views the user history as sequential information and has the ability to recognize usage pattern typical to certain group of items, e.g. to automatically tell apart product types that are typically purchased repetitively or once. Experiments performed on five implicit datasets (LastFM 1K, Grocery, VoD, and "implicitized" Netflix and MovieLens 10M) show that by integrating context-aware information with our factorization framework into the state-of-the-art implicit recommender algorithm the recommendation quality improves significantly.

Subfields: Computational Mathematics, Electrical and Electronic Engineering, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mathematics

In Electrical and Electronic Engineering

In Information Systems

Citations in the corpus

Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks (2017, background): “For example, in the context of a sale, items similar to a sold item are complementary items [7].”
Recurrent Neural Networks with Top-k Gains for Session-based Recommendations (2017, neutral): “Recall also usually correlates well with important online KPIs, such as click-through rate (CTR)[9, 14].”
Session-based Recommendations with Recurrent Neural Networks (2015, neutral): “Recall also usually correlates well with important online KPIs, such as click-through rate (CTR)(Liu et al., 2012; Hidasi & Tikk, 2012).”
Online Machine Learning in Big Data Streams (2018, methodology): “timization method for matrix factorization models, in which for a ﬁxed Q, we compute the optimal P, then for a ﬁxed P, the optimal Q, repeatedly until certain stopping criteria are met. Hidasi et al. [112, 111, 113] introduced several variants of ALS-based optimization schemes to incorporate context”
Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks (2017, background): “This is an accurate model for certain practical scenarios where no recommendation is highlighted and their absolute order does not matter, and strongly correlates with important KPIs such as CTR [6].”
Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations (2016, background): “Recall also usually correlates well with important online KPIs, such as click-through rate (CTR)[8].”
Iterative Splits of Quadratic Bounds for Scalable Binary Tensor Factorization (2014, methodology): “…are: • For matrix and tensor factorization models learned by minimizing the squared loss, we show that all the algorithms can beneﬁt from this speedup, i.e. it is not restricted to the alternating least square algorithm of [8], • We propose a new algorithm to minimize non-quadratic losses.”
Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks (2019, unknown): “listens-to-which song information [18].”